© 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. 4-RES-JB
    11. 15201
    Prev
    Next
    INDEX
    Explanations

    verbs related to action or change

    oai_token-act-pair · gpt-3.5-turbo

    gerunds or present participles related to actions or processes

    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
    lander
    -0.73
    enegger
    -0.71
    agar
    -0.66
    ordan
    -0.65
    imov
    -0.65
    alm
    -0.64
     nomine
    -0.64
     Stout
    -0.63
    ologne
    -0.62
    ratom
    -0.60
    POSITIVE LOGITS
    sticks
    0.72
    onite
    0.69
    leon
    0.65
    lain
    0.65
     flakes
    0.62
    opol
    0.61
    obos
    0.61
    anism
    0.61
     grou
    0.60
    pots
    0.59
    Activations Density 0.056%

    No Known Activations