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. 6-RES-JB
    6. 3206
    Prev
    Next
    INDEX
    Explanations

    bug fixes and software improvements

    oai_token-act-pair · gpt-3.5-turbo

    references to bug fixes and software maintenance

    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
    igion
    -0.84
    ructose
    -0.79
    educ
    -0.74
    ategic
    -0.74
    omsky
    -0.73
    aucas
    -0.73
    pin
    -0.70
    iolet
    -0.70
    gary
    -0.70
    stellar
    -0.70
    POSITIVE LOGITS
     workaround
    1.03
     bug
    0.99
    fixes
    0.95
     CVE
    0.93
     bugs
    0.88
    bug
    0.87
     fixes
    0.83
     Bugs
    0.82
    fix
    0.82
     [*]
    0.82
    Activations Density 0.148%

    No Known Activations