© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 11329
    Prev
    Next
    INDEX
    Explanations

    content that undergoes some form of examination or assessment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "review" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Torrent
    -0.77
    âĹ¼
    -0.77
    ña
    -0.75
    apo
    -0.73
    bott
    -0.73
    enos
    -0.70
    inos
    -0.70
    escape
    -0.68
    âĺĨ
    -0.68
    Translation
    -0.67
    POSITIVE LOGITS
     whether
    0.98
     feasibility
    0.92
    ively
    0.89
     carefully
    0.88
     closely
    0.81
     how
    0.76
     favorably
    0.76
     thoroughly
    0.76
    matically
    0.75
     aspects
    0.74
    Activations Density 0.108%

    No Known Activations