© 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. 14803
    Prev
    Next
    INDEX
    Explanations

    technical terms and names with specific characters and patterns

    oai_token-act-pair · gpt-3.5-turbo

    specific sequences of letters or characters that may represent names or unique 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
     predec
    -0.75
     cryst
    -0.71
    theless
    -0.69
    imeters
    -0.65
    avorite
    -0.63
    achev
    -0.63
     artif
    -0.60
     calories
    -0.60
     Thumbnails
    -0.59
     GOODMAN
    -0.59
    POSITIVE LOGITS
     Rowling
    0.83
    eki
    0.80
    schild
    0.73
    dan
    0.73
    etus
    0.72
    strings
    0.70
    unal
    0.70
    zyk
    0.70
    owicz
    0.69
     Marriott
    0.68
    Activations Density 0.315%

    No Known Activations