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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13862
    Prev
    Next
    INDEX
    Explanations

    references to events centered around the concept of a festival named "Trimurti Festival."

    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
    127
    +0.20
    0.7%
    128
    +0.18
    0.6%
    94
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.20
    0.06
    128
    +0.18
    0.06
    346
    +0.14
    0.06
    Negative Logits
    ELS
    -1.08
    âĸ¬âĸ¬
    -0.88
    LEY
    -0.87
    ORGE
    -0.85
     Mechdragon
    -0.84
    lishing
    -0.84
    ELD
    -0.83
    eers
    -0.83
     arts
    -0.83
    ãģ®éŃĶ
    -0.82
    POSITIVE LOGITS
    umps
    1.53
    ainer
    1.50
    ained
    1.47
    unks
    1.44
    acer
    1.43
    itton
    1.38
    ains
    1.36
    umble
    1.35
    usted
    1.34
    acers
    1.34
    Activations Density 1.120%

    No Known Activations