© 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. 2-RES-JB
    11. 383
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly first names

    oai_token-act-pair · gpt-4-turbo

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of people mentioned in relation to events or opinions

    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
    ãĥ¼ãĥ³
    -0.85
    igion
    -0.79
     td
    -0.78
    ruction
    -0.75
    ague
    -0.75
    ebook
    -0.72
    ãĥ¢
    -0.72
    mediated
    -0.68
     diarr
    -0.66
    itri
    -0.65
    POSITIVE LOGITS
     Hank
    0.88
    enstein
    0.73
    heon
    0.73
    keye
    0.72
    ukong
    0.72
    iamond
    0.70
     Hawks
    0.70
    alach
    0.69
    buster
    0.68
    ilda
    0.68
    Activations Density 0.016%

    No Known Activations