© 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. 6-RES-JB
    11. 5100
    Prev
    Next
    INDEX
    Explanations

    references to the website IMDb

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "IMDB" or related references to a film rating or review context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    velt
    -0.78
    ieve
    -0.76
    halla
    -0.73
    nown
    -0.73
    ieves
    -0.72
    rooms
    -0.70
    yards
    -0.66
    ingen
    -0.65
    isson
    -0.64
    atan
    -0.63
    POSITIVE LOGITS
    MED
    1.17
    PLIC
    1.12
    HO
    1.09
    PLE
    1.08
    PLIED
    1.04
    AX
    1.02
    MY
    1.02
    PROV
    0.98
    ITED
    0.97
    BO
    0.96
    Activations Density 0.018%

    No Known Activations