© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6878
    Prev
    Next
    INDEX
    Explanations

    decisions made by individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to decisions made by individuals or entities

    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
    icas
    -0.65
    ingers
    -0.64
    ubric
    -0.64
     havoc
    -0.64
    icum
    -0.63
    aband
    -0.63
    uction
    -0.63
    ights
    -0.61
    ighth
    -0.61
    zona
    -0.61
    POSITIVE LOGITS
     makers
    0.99
     to
    0.99
     maker
    0.80
    makers
    0.75
    making
    0.75
     regarding
    0.73
    maker
    0.72
     decision
    0.71
    abl
    0.71
     not
    0.71
    Activations Density 0.045%

    No Known Activations