© 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. 11-RES-JB
    11. 17043
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and coding

    oai_token-act-pair · gpt-3.5-turbo

    instances of programming terminology related to variable and function naming conventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mud
    -0.84
    tics
    -0.75
    mil
    -0.74
    zees
    -0.74
     Canaver
    -0.74
    bots
    -0.72
     Tanz
    -0.72
     Carroll
    -0.71
    odore
    -0.69
    ammy
    -0.68
    POSITIVE LOGITS
     parameter
    1.38
    Parameter
    1.30
     parameters
    1.30
     argument
    1.25
     arguments
    1.23
     value
    1.23
     values
    1.23
     args
    1.23
     boolean
    1.22
     params
    1.17
    Activations Density 0.185%

    No Known Activations