© 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. 7340
    Prev
    Next
    INDEX
    Explanations

    specific instances where something is being produced or created

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "produce" and its variations

    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
    laus
    -0.89
    imb
    -0.70
    nee
    -0.70
    phe
    -0.68
    bi
    -0.67
     Hilbert
    -0.66
    ede
    -0.65
    leans
    -0.65
    uyomi
    -0.63
    achine
    -0.63
    POSITIVE LOGITS
    女
    0.91
    ivity
    0.88
    Output
    0.85
    encers
    0.83
     output
    0.78
     outputs
    0.75
    Quality
    0.74
     offspring
    0.73
     produce
    0.72
    furt
    0.72
    Activations Density 0.815%

    No Known Activations