© 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. 7-RES-JB
    11. 3078
    Prev
    Next
    INDEX
    Explanations

    phrases describing additional information or items in a list

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ople
    -0.80
    ione
    -0.75
    cko
    -0.75
    Ñı
    -0.74
    ãĤ¢ãĥ«
    -0.72
    ogyn
    -0.71
    èĢħ
    -0.69
    agog
    -0.69
    aucus
    -0.68
    onica
    -0.66
    POSITIVE LOGITS
     besides
    0.69
     also
    0.64
     other
    0.62
     anecd
    0.62
     includ
    0.61
     moreover
    0.60
    mentioned
    0.59
     secretaries
    0.59
    recent
    0.59
     ALSO
    0.58
    Activations Density 0.160%

    No Known Activations