© 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. 3-RES-JB
    11. 11514
    Prev
    Next
    INDEX
    Explanations

    instances of the word "awaken" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "take."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mson
    -0.72
    phal
    -0.67
    encia
    -0.64
    BILITIES
    -0.61
    pt
    -0.61
    pton
    -0.60
    heter
    -0.59
    psc
    -0.59
    oteric
    -0.59
    pora
    -0.59
    POSITIVE LOGITS
    alia
    0.80
    edIn
    0.79
    umber
    0.78
    ede
    0.76
    iak
    0.74
    aken
    0.71
    fold
    0.69
    atche
    0.68
    rown
    0.67
    EY
    0.67
    Activations Density 0.015%

    No Known Activations