© 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. 9-RES-JB
    11. 15688
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to previous seasons or time periods in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roots
    -0.69
    alth
    -0.69
    ocks
    -0.68
    ongs
    -0.67
    baugh
    -0.66
    IRC
    -0.66
    oller
    -0.65
    ansk
    -0.65
    cil
    -0.65
    hess
    -0.64
    POSITIVE LOGITS
     week
    1.32
     year
    1.31
     month
    1.20
     season
    1.14
     night
    1.12
     weekend
    1.11
     semester
    1.04
     decade
    1.00
     yr
    0.98
     minute
    0.95
    Activations Density 0.062%

    No Known Activations