© 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. 8-RES-JB
    11. 8458
    Prev
    Next
    INDEX
    Explanations

    phrases related to additional information or resources

    oai_token-act-pair · gpt-3.5-turbo

    references to additional content or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.75
    generic
    -0.70
    ÅĤ
    -0.67
    rpm
    -0.66
     Gone
    -0.65
    cat
    -0.64
    bows
    -0.64
    FORE
    -0.64
    same
    -0.63
    athon
    -0.63
    POSITIVE LOGITS
    judicial
    1.04
     layers
    0.94
     impetus
    0.92
     installments
    0.86
     dimensions
    0.83
    ordinary
    0.82
     information
    0.81
     avenues
    0.80
     manpower
    0.79
     funds
    0.78
    Activations Density 0.033%

    No Known Activations