© 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. 4158
    Prev
    Next
    INDEX
    Explanations

    starting phrases or items indicating a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    technical or contextual terms related to "second" and its significance in a discussion

    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
    ITED
    -0.61
    Grab
    -0.60
    GA
    -0.60
    #$
    -0.58
    "},"
    -0.57
    ASC
    -0.57
    Pool
    -0.56
    ENC
    -0.55
    natureconservancy
    -0.55
    Sab
    -0.54
    POSITIVE LOGITS
    hetically
    0.94
    arily
    0.91
     importantly
    0.77
    ally
    0.75
    ately
    0.73
    thodox
    0.71
    ingly
    0.69
     secondly
    0.69
    hetic
    0.69
    ,
    0.69
    Activations Density 0.058%

    No Known Activations