© 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. 13778
    Prev
    Next
    INDEX
    Explanations

    scenarios or potential situations

    oai_token-act-pair · gpt-3.5-turbo

    references to various scenarios or hypothetical situations

    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
    artisan
    -0.88
    enfranch
    -0.81
    aina
    -0.78
    ances
    -0.75
    vals
    -0.73
    cott
    -0.73
    onso
    -0.73
    algia
    -0.72
    gow
    -0.71
    itsch
    -0.71
    POSITIVE LOGITS
     scenario
    1.26
     scenarios
    1.25
     involving
    1.06
     wherein
    1.03
     unfolding
    0.96
     whereby
    0.93
     unfold
    0.92
     depicted
    0.84
     simulations
    0.82
     unfolds
    0.81
    Activations Density 0.084%

    No Known Activations