© 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. 8-RES-JB
    11. 20260
    Prev
    Next
    INDEX
    Explanations

    dates or numbers indicating a specific day of a month

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and specific historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cellence
    -0.91
    ãĥĦ
    -0.75
    paralle
    -0.72
    ometers
    -0.71
    wiki
    -0.70
    igham
    -0.70
    ifles
    -0.69
    urus
    -0.69
    usa
    -0.68
    uria
    -0.68
    POSITIVE LOGITS
     deadline
    1.05
     edition
    1.03
     expiration
    1.00
     installment
    0.95
     arrival
    0.93
     departure
    0.93
     timeframe
    0.89
     announcement
    0.89
     sunset
    0.87
     episode
    0.86
    Activations Density 0.094%

    No Known Activations