© 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 Local
    9. 6-RES_SCL-AJT
    11. 35610
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and judgement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.16
    0.8%
    393
    +0.14
    0.7%
    550
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.16
    0.38
    566
    +0.14
    0.20
    138
    +0.10
    0.19
    Negative Logits
    haul
    -0.64
    oided
    -0.62
     largeDownload
    -0.58
    ãĥ©ãĥ³
    -0.55
    iop
    -0.54
    ortment
    -0.54
    tnc
    -0.53
    ription
    -0.53
    YES
    -0.52
    Winged
    -0.52
    POSITIVE LOGITS
     anymore
    1.68
     nor
    1.35
     slightest
    1.08
    yet
    0.96
     anywhere
    0.94
     any
    0.94
     whatsoever
    0.93
     necessarily
    0.93
     anything
    0.93
     bothered
    0.92
    Activations Density 19.282%

    No Known Activations