© 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. 2245
    Prev
    Next
    INDEX
    Explanations

    descriptions related to people's personal and professional background

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate the end of statements or complete thoughts

    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
     consolation
    -0.88
     tremend
    -0.88
     optional
    -0.76
     nodd
    -0.76
     calf
    -0.76
     challeng
    -0.75
     corrid
    -0.75
     viability
    -0.74
     feasible
    -0.73
     exclus
    -0.73
    POSITIVE LOGITS
     Born
    1.49
     He
    1.45
     His
    1.42
     She
    1.39
     Previously
    1.37
     Prior
    1.32
     During
    1.32
     Originally
    1.31
     Known
    1.30
     Serving
    1.26
    Activations Density 0.255%

    No Known Activations