© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 32569
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent or distressing acts

    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
    99
    +0.10
    0.4%
    759
    +0.10
    0.4%
    699
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.10
    0.13
    288
    +0.10
    0.17
    291
    +0.10
    0.09
    Negative Logits
     Cosponsors
    -0.73
     Sparkle
    -0.71
    ĸļ
    -0.68
     Sigma
    -0.67
    sbm
    -0.66
     subp
    -0.65
    quickShipAvailable
    -0.65
     Mahjong
    -0.65
     Standing
    -0.64
    accompan
    -0.63
    POSITIVE LOGITS
     throats
    0.81
    hoe
    0.76
    pipe
    0.71
    waters
    0.71
    adle
    0.71
    ports
    0.70
    liest
    0.70
    mouth
    0.69
    bones
    0.68
    vale
    0.66
    Activations Density 5.667%

    No Known Activations