© 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. 23803
    Prev
    Next
    INDEX
    Explanations

    Roman numerals representing chapters or sections

    oai_token-act-pair · gpt-3.5-turbo

    references to sequels or installments in a series

    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
    boards
    -1.01
    board
    -0.95
    cho
    -0.75
    places
    -0.73
    lins
    -0.72
    chant
    -0.71
    faced
    -0.71
    liest
    -0.71
    itionally
    -0.69
    initialized
    -0.68
    POSITIVE LOGITS
    III
    1.26
    II
    1.07
    FY
    0.94
    IV
    0.77
     Britann
    0.77
    HF
    0.75
     Aus
    0.72
    ACA
    0.72
    VII
    0.72
    RC
    0.70
    Activations Density 0.050%

    No Known Activations