© 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. 34871
    Prev
    Next
    INDEX
    Explanations

    phrases related to covering costs or hiding information

    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
    +0.12
    0.6%
    636
    +0.11
    0.5%
    511
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.28
    636
    +0.11
    0.07
    160
    +0.09
    0.20
    Negative Logits
     recomm
    -0.71
    rious
    -0.66
    efficients
    -0.65
    nir
    -0.63
    friend
    -0.61
     onwards
    -0.60
     rever
    -0.59
    memory
    -0.58
    Eng
    -0.58
    isoft
    -0.58
    POSITIVE LOGITS
     bases
    0.94
    topic
    0.72
     gaps
    0.71
     entirety
    0.71
    ategories
    0.70
    phia
    0.68
     Mellon
    0.68
     gap
    0.67
    idential
    0.66
    eatures
    0.65
    Activations Density 14.474%

    No Known Activations