© 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. 3686
    Prev
    Next
    INDEX
    Explanations

    number sequences preceded by special characters

    oai_token-act-pair · gpt-3.5-turbo

    the symbol or character representation of certain numerical or coded values

    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
    entious
    -0.85
    nces
    -0.84
    ritic
    -0.83
    ahime
    -0.79
    rites
    -0.78
    idy
    -0.75
    keeping
    -0.72
    aceutical
    -0.71
    wagen
    -0.71
    interrupted
    -0.70
    POSITIVE LOGITS
    LAB
    0.85
     magnification
    0.80
     Expand
    0.80
    cus
    0.69
    _>
    0.66
    Python
    0.63
    Pict
    0.61
    [[
    0.61
    ghai
    0.59
     guiIcon
    0.58
    Activations Density 0.008%

    No Known Activations