© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 15252
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "si" or the name "Schr" with some numerical values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the syllable "si" in words

    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
    side
    -0.77
    icates
    -0.74
    icity
    -0.68
    icas
    -0.67
    killer
    -0.65
    grown
    -0.64
     Second
    -0.64
    icative
    -0.63
    pages
    -0.63
    landish
    -0.63
    POSITIVE LOGITS
    pling
    1.26
    plings
    0.99
    zona
    0.96
    pler
    0.96
    plin
    0.89
    ption
    0.86
    asa
    0.85
    ples
    0.84
    pper
    0.84
    pton
    0.83
    Activations Density 0.012%

    No Known Activations