© 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. 4-RES-JB
    11. 7551
    Prev
    Next
    INDEX
    Explanations

    references to architectural structures and features

    oai_token-act-pair · gpt-3.5-turbo

    references to urban development and public spaces

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

    No Comments

    Negative Logits
     saliva
    -0.77
    Downloadha
    -0.74
     semen
    -0.71
     pardon
    -0.70
     plagiar
    -0.69
     interrog
    -0.69
     vain
    -0.68
    imester
    -0.67
     counterfe
    -0.67
     neurolog
    -0.67
    POSITIVE LOGITS
     zoning
    0.84
    atown
    0.82
    cape
    0.82
     plaza
    0.82
     Plaza
    0.80
    Square
    0.78
    Layout
    0.77
     perched
    0.76
     entrances
    0.74
    Construction
    0.74
    Activations Density 0.348%

    No Known Activations