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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 23084
    Prev
    Next
    INDEX
    Explanations

    pieces of code involving functions and their arguments

    oai_token-act-pair · gpt-3.5-turbo

    instances of opening parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylum
    -0.79
    entimes
    -0.78
    âĢij
    -0.72
     incarn
    -0.70
     handc
    -0.69
     wart
    -0.68
     confessions
    -0.68
     ransom
    -0.67
     veterin
    -0.63
     whis
    -0.62
    POSITIVE LOGITS
    ...)
    0.99
    ())
    0.96
    default
    0.88
    username
    0.86
     )
    0.82
    verb
    0.79
    src
    0.78
    input
    0.76
    msg
    0.76
    checked
    0.76
    Activations Density 0.034%

    No Known Activations