© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    words related to planned, suggested, predicted, or intended outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to intentions or objectives

    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
    itaire
    -0.82
    actionDate
    -0.81
    ertodd
    -0.79
    ilk
    -0.78
    erie
    -0.78
    @#&
    -0.75
    ̶
    -0.75
    zona
    -0.74
    atever
    -0.73
    Cola
    -0.73
    POSITIVE LOGITS
     lifespan
    0.96
     Parenthood
    0.92
     timetable
    0.87
     successor
    0.85
     outcome
    0.85
     timeframe
    0.85
     departure
    0.84
     timeline
    0.83
     boundaries
    0.82
     amount
    0.82
    Activations Density 0.127%

    No Known Activations