© 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. 7762
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people named "Evans."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Evans."

    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
    izen
    -0.93
    fare
    -0.77
    unal
    -0.71
    acts
    -0.71
    pees
    -0.69
    eways
    -0.69
    aphael
    -0.69
    rous
    -0.68
    ries
    -0.65
    ographies
    -0.64
    POSITIVE LOGITS
    aunders
    0.91
    '
    0.87
    ville
    0.86
    burg
    0.85
    burgh
    0.84
    boro
    0.79
    olver
    0.79
    dale
    0.78
    ullivan
    0.76
    sey
    0.76
    Activations Density 0.041%

    No Known Activations