Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 620
    Prev
    Next
    INDEX
    Explanations

    social media and website links

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    664
    +0.10
    0.7%
    19
    +0.06
    0.4%
    390
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.00
    626
    +0.06
    0.00
    606
    +0.06
    0.01
    Negative Logits
    hn
    -0.59
    HUD
    -0.49
    swick
    -0.46
     nav
    -0.46
     Homes
    -0.46
    KNOWN
    -0.45
    vich
    -0.44
    MM
    -0.43
    sburg
    -0.43
    bye
    -0.43
    POSITIVE LOGITS
    ileged
    0.49
     Anthrop
    0.47
     Alchemist
    0.47
    uton
    0.46
    osterone
    0.46
    ilege
    0.44
    ylene
    0.43
     ageing
    0.42
    Union
    0.42
    ativity
    0.42
    Activations Density 0.008%

    No Known Activations