© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7608
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Mull" in various contexts

    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
    merce
    -0.72
    ãĥ¥
    -0.70
     Scotia
    -0.65
    ced
    -0.64
    nerg
    -0.63
    ters
    -0.61
    paralle
    -0.61
    CE
    -0.60
    cence
    -0.60
    zig
    -0.59
    POSITIVE LOGITS
    sburg
    1.27
    igan
    1.17
    igans
    1.15
    abal
    1.11
    iard
    1.08
    aby
    1.07
    abies
    1.04
    owship
    1.03
    inx
    0.93
    uminati
    0.92
    Activations Density 0.050%

    No Known Activations