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

    Neuronpedia

    Jacobian LensNEW
    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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 891
    Prev
    Next
    INDEX
    Explanations

    references to individuals named "McClure" or "McClaren"

    oai_token-act-pair · gpt-3.5-turbo

    words or names that start with "McCl"

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    216
    +0.15
    0.6%
    500
    +0.14
    0.5%
    137
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.19
    326
    +0.14
    0.15
    659
    +0.13
    0.09
    Negative Logits
    ITED
    -0.91
    qua
    -0.90
    friend
    -0.86
    ATA
    -0.84
    abilities
    -0.81
     Gandhi
    -0.79
    oking
    -0.79
    leader
    -0.77
    EGA
    -0.77
     patronage
    -0.76
    POSITIVE LOGITS
    hess
    1.06
    ŃĶ
    0.99
    ©¶æ¥µ
    0.98
    ĵĺ
    0.95
    iffs
    0.92
    witz
    0.91
    eness
    0.90
    kees
    0.89
    ©
    0.89
    ãĥ£
    0.88
    Activations Density 3.378%

    No Known Activations