© 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. 3-RES-JB
    11. 11466
    Prev
    Next
    INDEX
    Explanations

    numerical references associated with academic or technical information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of square brackets

    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
     Register
    -0.71
     Ingredients
    -0.67
     showc
    -0.66
    otine
    -0.66
     hog
    -0.66
     Cookies
    -0.65
    ulkan
    -0.63
    aron
    -0.62
     Mean
    -0.62
     Alam
    -0.61
    POSITIVE LOGITS
    src
    0.92
    sic
    0.83
    Pg
    0.83
    sed
    0.80
    âĢ¦]
    0.78
    tm
    0.77
    ...]
    0.76
    feet
    0.75
    loaded
    0.74
    debian
    0.74
    Activations Density 0.062%

    No Known Activations