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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4334
    Prev
    Next
    INDEX
    Explanations

    natural disaster-related information, specifically about landslides and mudslides

    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
    +0.26
    1.2%
    459
    +0.12
    0.5%
    486
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    618
    +0.26
    0.18
    393
    +0.12
    0.35
    644
    +0.11
    0.14
    Negative Logits
     invade
    -0.78
     collusion
    -0.74
     Presidential
    -0.71
     invading
    -0.70
     assassination
    -0.70
     appointing
    -0.70
    eus
    -0.69
     compromising
    -0.68
     nominees
    -0.68
    establishment
    -0.67
    POSITIVE LOGITS
    é¾
    0.99
     granddaughter
    0.83
     homeowner
    0.82
     grandmother
    0.80
     careg
    0.79
     grandson
    0.79
     Labrador
    0.77
     Cree
    0.76
    Dispatch
    0.75
    veland
    0.74
    Activations Density 23.140%

    No Known Activations