© 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. 6-RES-JB
    11. 12174
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics mentioning percentages or amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, especially those relating to statistics or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.83
    tumblr
    -0.70
    ions
    -0.65
    urger
    -0.63
    riel
    -0.63
    ¥µ
    -0.63
     POLITICO
    -0.61
     novelist
    -0.60
    fur
    -0.60
    ilant
    -0.59
    POSITIVE LOGITS
    00
    0.85
    atural
    0.78
    ielding
    0.76
    %-
    0.75
    ature
    0.75
    umber
    0.71
    50
    0.70
    IFE
    0.70
    ession
    0.69
    mares
    0.69
    Activations Density 0.038%

    No Known Activations