© 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 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. 8-RES-JB
    11. 22373
    Prev
    Next
    INDEX
    Explanations

    references to IM, likely referring to the website IMDb

    oai_token-act-pair · gpt-3.5-turbo

    references to the Internet Movie Database (IMDb)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.73
    quez
    -0.69
    tenance
    -0.69
    velt
    -0.68
     Borough
    -0.67
    ieve
    -0.67
    halla
    -0.67
    ieves
    -0.66
    rooms
    -0.66
    ¶ħ
    -0.66
    POSITIVE LOGITS
    MED
    1.14
    HO
    1.13
    PLIC
    1.11
    Db
    1.05
    MAC
    0.97
    PROV
    0.97
    PLE
    0.94
    PU
    0.94
    BO
    0.93
    AX
    0.92
    Activations Density 0.029%

    No Known Activations