Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34455
    Prev
    Next
    INDEX
    Explanations

    information related to shootings and violent incidents

    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
    +0.14
    0.6%
    152
    +0.11
    0.5%
    627
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.30
    393
    +0.11
    0.32
    703
    +0.09
    0.08
    Negative Logits
    taboola
    -0.81
    heit
    -0.80
     Administ
    -0.80
    ional
    -0.78
    Trade
    -0.78
    Lost
    -0.76
    isd
    -0.75
    soType
    -0.74
    JV
    -0.74
     Cosponsors
    -0.71
    POSITIVE LOGITS
     espresso
    0.94
     unarmed
    0.90
    ovie
    0.82
     adrenaline
    0.80
     blaster
    0.79
     torped
    0.79
     bullets
    0.79
     pellets
    0.78
     lasers
    0.77
     lightning
    0.77
    Activations Density 17.733%

    No Known Activations