© 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. 9-RES-JB
    11. 8985
    Prev
    Next
    INDEX
    Explanations

    API function calls or code syntax elements

    oai_token-act-pair · gpt-3.5-turbo

    opening and closing parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kindly
    -0.81
     equival
    -0.68
     clinch
    -0.67
     ransom
    -0.67
     wart
    -0.65
     microsc
    -0.65
     whip
    -0.65
     dece
    -0.64
     raiding
    -0.63
     Anglic
    -0.63
    POSITIVE LOGITS
    ())
    1.16
    ctx
    1.13
    std
    1.10
    input
    1.09
    ...)
    1.09
    function
    1.09
    false
    1.07
    context
    1.06
    true
    1.06
    ['
    1.03
    Activations Density 0.039%

    No Known Activations