© 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. 8-RES-JB
    11. 12003
    Prev
    Next
    INDEX
    Explanations

    references to legal cases or individuals related to legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals involved in a case or situation

    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
    plain
    -0.81
     ado
    -0.61
    XXXX
    -0.60
    atari
    -0.60
     Crus
    -0.60
    inct
    -0.59
     parted
    -0.59
     Virgin
    -0.58
    atted
    -0.58
    bery
    -0.58
    POSITIVE LOGITS
    strom
    0.90
    seys
    0.80
    ás
    0.73
    holm
    0.72
    nea
    0.72
    kson
    0.71
    lein
    0.71
    odynam
    0.69
    reens
    0.69
    DEM
    0.68
    Activations Density 0.056%

    No Known Activations