© 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 EvalsExportsinterp-engineNEWAPI 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. 31901
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and governmental entities, particularly related to weather events

    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
    331
    +0.13
    0.6%
    488
    +0.12
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.26
    575
    +0.12
    0.18
    76
    +0.12
    0.13
    Negative Logits
    linger
    -0.79
     Myster
    -0.78
    thora
    -0.78
    eport
    -0.74
    arth
    -0.74
    eful
    -0.73
    enery
    -0.72
    hops
    -0.72
    rencies
    -0.72
    uckland
    -0.72
    POSITIVE LOGITS
    wide
    1.14
     approval
    0.94
     officials
    0.91
     insiders
    0.88
     discretion
    0.88
     disapproval
    0.86
     misconduct
    0.81
     staffers
    0.81
     personnel
    0.81
     goodwill
    0.81
    Activations Density 9.716%

    No Known Activations