© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 46030
    Prev
    Next
    INDEX
    Explanations

    information related to events and actions in various fields such as politics, entertainment, and literature

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.21
    1.0%
    195
    +0.13
    0.6%
    679
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.40
    679
    +0.13
    0.28
    255
    +0.11
    0.18
    Negative Logits
    interstitial
    -0.65
     harbour
    -0.59
     receiving
    -0.58
     polar
    -0.57
     harbor
    -0.56
    shore
    -0.55
     beginning
    -0.55
     fin
    -0.55
     leve
    -0.54
     pre
    -0.54
    POSITIVE LOGITS
    soever
    1.04
     Matters
    0.79
     else
    0.73
    beit
    0.69
    resa
    0.69
    Things
    0.67
    croft
    0.67
     transpired
    0.67
    nces
    0.66
     happens
    0.66
    Activations Density 12.863%

    No Known Activations