© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20880
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Abe" followed by numbers, potentially referring to different individuals or entities with the name "Abe."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Mugabe"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phis
    -0.85
    prus
    -0.68
    ivities
    -0.66
     irony
    -0.65
    iple
    -0.63
     Dragonbound
    -0.63
    neapolis
    -0.62
    ipt
    -0.62
    matic
    -0.60
    ivity
    -0.60
    POSITIVE LOGITS
    abe
    1.29
    legates
    1.02
    legate
    1.00
    deen
    0.97
    ça
    0.81
    \\\\
    0.81
    ards
    0.79
    FORE
    0.78
    verning
    0.77
    erc
    0.76
    Activations Density 0.007%

    No Known Activations