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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 731
    Prev
    Next
    INDEX
    Explanations

    details related to criminal incidents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    104
    +0.16
    0.5%
    551
    +0.14
    0.5%
    158
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.16
    0.07
    104
    +0.14
    0.05
    590
    +0.12
    0.05
    Negative Logits
     monopol
    -1.10
     filib
    -1.01
     hegemony
    -0.99
     opp
    -0.97
     shrew
    -0.96
    bench
    -0.95
    âĹ
    -0.94
     rebell
    -0.94
    女
    -0.94
    lip
    -0.94
    POSITIVE LOGITS
     Authorities
    1.24
     coroner
    1.19
     evacuated
    1.19
     Trooper
    1.16
     Lt
    1.13
     paramedics
    1.12
    EMS
    1.12
     apprehended
    1.11
     Officers
    1.08
     troopers
    1.08
    Activations Density 2.076%

    No Known Activations