© 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. 12802
    Prev
    Next
    INDEX
    Explanations

    web or email addresses containing the term "comp"

    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
    137
    +0.16
    0.6%
    288
    +0.13
    0.5%
    615
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.10
    220
    +0.13
    0.05
    137
    +0.13
    0.04
    Negative Logits
    hao
    -0.89
    der
    -0.88
    velt
    -0.84
    lain
    -0.83
    thur
    -0.83
     Mens
    -0.81
    mares
    -0.80
    soever
    -0.80
    vae
    -0.78
    kar
    -0.78
    POSITIVE LOGITS
    ensation
    1.57
    assion
    1.39
    etitive
    1.37
    etition
    1.31
    endium
    1.30
    atibility
    1.27
    ressor
    1.26
    onential
    1.24
    atible
    1.19
    ression
    1.18
    Activations Density 1.328%

    No Known Activations