© 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. 11-RES-JB
    11. 9856
    Prev
    Next
    INDEX
    Explanations

    numerical facts and statistics related to frequency or quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to quantity or frequency in relation to people or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izo
    -0.69
    ypes
    -0.68
    afort
    -0.64
    esy
    -0.63
    details
    -0.63
    UFF
    -0.63
    èª
    -0.62
    iets
    -0.60
     Plans
    -0.60
     Limits
    -0.58
    POSITIVE LOGITS
     year
    1.64
     month
    1.44
     day
    1.42
     minute
    1.29
     week
    1.28
     hour
    1.26
    year
    1.23
     decade
    1.21
     YEAR
    1.17
     weekday
    1.14
    Activations Density 0.084%

    No Known Activations