© 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. 23878
    Prev
    Next
    INDEX
    Explanations

    terms related to technical codes or symbols

    oai_token-act-pair · gpt-3.5-turbo

    elements related to fashion or style indicators

    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
    eller
    -0.71
    enberg
    -0.65
    lier
    -0.61
     Mysteries
    -0.60
    zes
    -0.60
     footing
    -0.60
    lli
    -0.58
    bern
    -0.58
     bend
    -0.57
    ryu
    -0.57
    POSITIVE LOGITS
    twitter
    0.73
    cffffcc
    0.72
    =#
    0.72
    ongyang
    0.68
    uably
    0.68
    ardless
    0.68
    utf
    0.64
    CVE
    0.64
    Balt
    0.64
    RIP
    0.64
    Activations Density 0.119%

    No Known Activations