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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20262
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases expressing strong emotions or commands

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory punctuation or expressions of strong emotion

    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
    ·
    -0.69
     negatives
    -0.64
     electrodes
    -0.63
     grips
    -0.62
    ©¶æ
    -0.62
     chairs
    -0.61
     stationary
    -0.60
     presses
    -0.59
     enriched
    -0.59
    asers
    -0.59
    POSITIVE LOGITS
    #$
    0.93
     âĢķ
    0.86
    /"
    0.85
    azon
    0.80
     exclaim
    0.77
     exclaimed
    0.74
     Answer
    0.73
    @#&
    0.72
    ilo
    0.68
     ["
    0.68
    Activations Density 0.021%

    No Known Activations