© 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. 10-RES-JB
    11. 21572
    Prev
    Next
    INDEX
    Explanations

    variable names in programming code

    oai_token-act-pair · gpt-3.5-turbo

    references to variables in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļé
    -0.85
    llah
    -0.84
    İ
    -0.81
    udeb
    -0.79
    furt
    -0.79
    Ķ
    -0.77
    Ĥª
    -0.76
    lyak
    -0.76
    HCR
    -0.74
    Crash
    -0.74
    POSITIVE LOGITS
     variables
    0.92
    variable
    0.83
     variable
    0.79
     bindings
    0.77
    izations
    0.73
    ials
    0.72
    uates
    0.70
     coefficients
    0.69
    wine
    0.69
     assignments
    0.69
    Activations Density 0.040%

    No Known Activations