© 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. 8-RES-JB
    11. 4559
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and syntactical elements within code snippets

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to programming functions and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cele
    -0.73
    drug
    -0.69
    女
    -0.67
     Roz
    -0.64
     Hilton
    -0.64
    interstitial
    -0.63
    £
    -0.63
     Bravo
    -0.62
    advertising
    -0.62
     Playboy
    -0.62
    POSITIVE LOGITS
     syntax
    1.21
     recursive
    1.19
     deprecated
    1.17
     implementations
    1.14
     runtime
    1.12
     debugging
    1.11
     configure
    1.10
     dependencies
    1.08
     workaround
    1.06
     Python
    1.06
    Activations Density 1.129%

    No Known Activations