© 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 EvalsExportsinterp-engineNEWAPI 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. 11281
    Prev
    Next
    INDEX
    Explanations

    exclamatory expressions and enthusiastic language

    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
    326
    +0.23
    0.8%
    274
    +0.17
    0.6%
    509
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.23
    0.05
    6
    +0.17
    0.07
    679
    +0.17
    0.07
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -1.02
    ommel
    -0.99
    uously
    -0.94
    atively
    -0.93
     democracies
    -0.90
    ocratic
    -0.90
    ezvous
    -0.87
     nav
    -0.87
     towel
    -0.86
    ãĥ³ãĤ¸
    -0.83
    POSITIVE LOGITS
    !!!!!
    1.16
    !/
    1.09
    cffffcc
    1.08
    php
    1.06
    SPEC
    1.04
    CONT
    1.01
    mmmm
    1.01
    nuts
    1.01
    DOWN
    1.01
    sym
    1.00
    Activations Density 1.307%

    No Known Activations