© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15980
    Prev
    Next
    INDEX
    Explanations

    numerical patterns with repeated digits

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the numeral "8" and related phrases

    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
    itton
    -0.73
    ãĥ¼ãĥĨ
    -0.70
    insula
    -0.69
    andise
    -0.69
    é¾įå¥ij士
    -0.67
     Lauder
    -0.67
     parach
    -0.67
     harmless
    -0.64
    ostics
    -0.63
    rison
    -0.60
    POSITIVE LOGITS
    192
    1.18
    989
    1.02
    98
    1.00
    90
    1.00
    een
    0.98
    ecause
    0.94
    79
    0.92
    57
    0.92
    58
    0.92
    eenth
    0.90
    Activations Density 0.053%

    No Known Activations