© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 17386
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings or requests for support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appeal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Benz
    -0.75
    fters
    -0.73
     Dirt
    -0.70
    Ñĥ
    -0.69
    miah
    -0.68
     Benz
    -0.68
    FT
    -0.66
    hours
    -0.65
     Chem
    -0.63
    BT
    -0.62
    POSITIVE LOGITS
     appeal
    1.06
    ocene
    0.83
     appealing
    0.83
     advis
    0.82
     appealed
    0.81
     appeals
    0.79
    ingly
    0.77
    minist
    0.77
     plea
    0.76
    ously
    0.75
    Activations Density 0.011%

    No Known Activations