© 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. 9-RES-JB
    11. 2232
    Prev
    Next
    INDEX
    Explanations

    terms related to forecasting or prediction

    oai_token-act-pair · gpt-3.5-turbo
    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
    ISM
    -0.73
     Chop
    -0.68
     shed
    -0.62
    OWS
    -0.62
     Dreams
    -0.62
     Turks
    -0.61
     Archdemon
    -0.60
     thumbs
    -0.60
     Isles
    -0.60
     Shed
    -0.59
    POSITIVE LOGITS
    erver
    1.40
    chool
    1.25
    umed
    1.20
    ervative
    1.20
    byter
    1.18
    umes
    1.18
    idium
    1.17
    erv
    1.14
    umer
    1.11
    umption
    1.11
    Activations Density 0.034%

    No Known Activations