© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13929
    Prev
    Next
    INDEX
    Explanations

    political and social vocabulary related to government actions and public policies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Layer 6 UMAP region: Local cluster above bottom line touching e2e-recon cluster - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.28
    1.7%
    679
    +0.12
    0.7%
    640
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.49
    6
    +0.12
    0.30
    679
    +0.08
    0.35
    Negative Logits
     transition
    -0.60
     maxim
    -0.55
     transitions
    -0.53
     lifes
    -0.52
     lvl
    -0.52
     regener
    -0.52
     diseng
    -0.51
    iencies
    -0.51
     agility
    -0.50
     optimum
    -0.49
    POSITIVE LOGITS
     Earlier
    0.71
     Notably
    0.67
     Yesterday
    0.65
     Particularly
    0.65
     Though
    0.65
     Critics
    0.64
     Specifically
    0.62
     Recent
    0.61
    ItemTracker
    0.60
    untled
    0.60
    Activations Density 19.481%

    No Known Activations