© 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. 10-RES-JB
    11. 2947
    Prev
    Next
    INDEX
    Explanations

    details related to people's performance or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to events or developments in progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ
    -0.75
    externalActionCode
    -0.70
     taxpayers
    -0.68
    .?
    -0.67
     taxpayer
    -0.67
    .</
    -0.66
     Customers
    -0.66
    *.
    -0.64
    .''.
    -0.63
    custom
    -0.62
    POSITIVE LOGITS
     spor
    0.92
     admittedly
    0.92
     sporadic
    0.90
     vaguely
    0.88
     vague
    0.87
     occasional
    0.86
     somewhat
    0.85
     decent
    0.84
     nicely
    0.84
     nice
    0.83
    Activations Density 1.247%

    No Known Activations