Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 881
    Prev
    Next
    INDEX
    Explanations

    variables in code snippets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "variable"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mares
    -0.91
    chwitz
    -0.86
    onian
    -0.79
    mind
    -0.78
    abad
    -0.78
    communications
    -0.75
    enough
    -0.74
    ctors
    -0.74
    reads
    -0.74
    eki
    -0.73
    POSITIVE LOGITS
     var
    3.27
     Var
    1.42
     func
    1.20
     vel
    1.12
     lac
    1.11
    Var
    1.11
     imperfect
    1.04
     val
    1.03
     vari
    1.01
     const
    1.01
    Activations Density 0.013%

    No Known Activations