© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6418
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings

    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
    583
    +0.12
    0.4%
    682
    +0.11
    0.4%
    412
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    618
    +0.12
    0.08
    412
    +0.11
    0.07
    764
    +0.11
    0.05
    Negative Logits
    ither
    -0.88
    merce
    -0.83
    ķ
    -0.83
    whatever
    -0.82
     irresistible
    -0.81
     sequels
    -0.78
    fml
    -0.78
     treaties
    -0.78
     incidental
    -0.76
    CLAIM
    -0.75
    POSITIVE LOGITS
     Photograph
    1.44
     REUTERS
    1.37
     pictured
    1.35
     Photo
    1.27
     photo
    1.26
     PHOTO
    1.23
     Courtesy
    1.23
     Wikimedia
    1.23
     flanked
    1.20
     Flickr
    1.20
    Activations Density 2.823%

    No Known Activations