© 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. 6757
    Prev
    Next
    INDEX
    Explanations

    technical and legal terms related to legislation and government documents

    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
    232
    +0.18
    0.6%
    667
    +0.15
    0.5%
    739
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.18
    0.05
    365
    +0.15
    0.03
    667
    +0.15
    0.03
    Negative Logits
     Cors
    -0.92
    20439
    -0.89
     Papers
    -0.89
     Dol
    -0.88
    ETHOD
    -0.88
     diplom
    -0.86
    çİĭ
    -0.83
    YP
    -0.83
    IPS
    -0.81
    GMT
    -0.81
    POSITIVE LOGITS
    mitted
    1.90
    sequent
    1.82
    sequently
    1.72
    stantial
    1.69
    marine
    1.64
    lime
    1.61
    versive
    1.51
    stant
    1.47
    mitting
    1.46
    scription
    1.45
    Activations Density 0.400%

    No Known Activations