© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14123
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and procedures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and special characters used in quotes and citations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     carriage
    -0.65
     LF
    -0.62
     Orchestra
    -0.60
     Victory
    -0.60
     Oss
    -0.59
     decimal
    -0.58
     Skydragon
    -0.57
     Sunny
    -0.57
     bed
    -0.57
     jug
    -0.57
    POSITIVE LOGITS
    that
    1.14
    of
    1.11
    without
    0.99
    between
    0.98
    against
    0.96
    within
    0.96
    into
    0.93
    from
    0.92
    onto
    0.91
    above
    0.91
    Activations Density 0.429%

    No Known Activations