© 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. 0-RES-JB
    6. 20392
    Prev
    Next
    INDEX
    Explanations

    words related to distribution or dispersion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spread."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VO
    -0.76
    qual
    -0.72
    retty
    -0.72
     Morrison
    -0.70
     Responsibility
    -0.69
    rie
    -0.69
     Guant
    -0.67
    nie
    -0.66
     respects
    -0.64
     Stevenson
    -0.64
    POSITIVE LOGITS
     spread
    3.96
     Spread
    2.84
     spreads
    2.70
    spread
    2.58
    Spread
    2.55
     spreading
    2.23
     dispersed
    1.35
     dissemin
    1.30
     dissemination
    1.30
    pread
    1.29
    Activations Density 0.028%

    No Known Activations