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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11288
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaking a situation, record, rule, or pattern

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve significant legislative actions or political events

    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
    enhagen
    -0.76
    00200000
    -0.69
    reau
    -0.68
    expr
    -0.66
    eton
    -0.65
    eers
    -0.63
    minist
    -0.62
     Reserved
    -0.62
    GREEN
    -0.61
     Matters
    -0.61
    POSITIVE LOGITS
     silence
    0.90
     seal
    0.90
     curfew
    0.83
     blockade
    0.82
     barrier
    0.82
     taboo
    0.78
     chain
    0.77
     mould
    0.77
     barriers
    0.77
     truce
    0.76
    Activations Density 0.121%

    No Known Activations