© 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 Local
    9. 6-RES_SCL-AJT
    11. 33411
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or scrutiny of authority figures, particularly in governmental or organizational contexts

    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
    228
    +0.11
    0.5%
    320
    +0.11
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.16
    38
    +0.11
    0.13
    183
    +0.10
    0.11
    Negative Logits
    anan
    -0.62
     fundament
    -0.57
    uli
    -0.57
     methodological
    -0.55
     Enhancement
    -0.55
     largeDownload
    -0.55
     motif
    -0.52
    Kings
    -0.52
     moratorium
    -0.51
     disclaimer
    -0.51
    POSITIVE LOGITS
     anymore
    1.33
     anywhere
    0.93
     nor
    0.92
     necessarily
    0.90
     bothered
    0.86
    icable
    0.80
    yet
    0.79
     bother
    0.78
     any
    0.78
     remotely
    0.77
    Activations Density 10.887%

    No Known Activations