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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2928
    Prev
    Next
    INDEX
    Explanations

    mentions of names related to politics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Abe" or variations thereof

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

    No Comments

    Negative Logits
    phis
    -0.96
    neapolis
    -0.90
    prus
    -0.87
    ivities
    -0.86
    ivity
    -0.85
    imates
    -0.80
    ivated
    -0.77
    iosity
    -0.75
    ivating
    -0.73
    ivan
    -0.72
    POSITIVE LOGITS
    legates
    0.91
    legate
    0.88
    FORE
    0.86
    zz
    0.80
    deen
    0.78
    \\\\
    0.72
    zzi
    0.70
    hold
    0.69
    erc
    0.68
    utics
    0.67
    Activations Density 0.014%

    No Known Activations