© 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. 4-RES-JB
    11. 3654
    Prev
    Next
    INDEX
    Explanations

    code syntax related to functions or loops

    oai_token-act-pair · gpt-3.5-turbo

    code syntax elements, particularly function definitions and parameters

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

    No Comments

    Negative Logits
    enta
    -0.78
    ween
    -0.75
    uga
    -0.75
    kai
    -0.75
    natureconservancy
    -0.74
    bern
    -0.73
    ¥µ
    -0.72
    matical
    -0.71
    Ĥª
    -0.71
    tin
    -0.70
    POSITIVE LOGITS
     ;
    0.97
    )))
    0.92
     =>
    0.91
     //[
    0.89
     {
    0.87
     }
    0.84
     ||
    0.82
    ))))
    0.80
     })
    0.79
     }}
    0.78
    Activations Density 0.049%

    No Known Activations