© 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. 0-RES-JB
    11. 16397
    Prev
    Next
    INDEX
    Explanations

    references to the version control system "Git."

    oai_token-act-pair · gpt-3.5-turbo
    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
    casters
    -0.71
    idium
    -0.69
     Paula
    -0.69
    uro
    -0.69
     blanket
    -0.67
     shaped
    -0.66
    wcs
    -0.66
     television
    -0.66
     telev
    -0.65
    ossier
    -0.65
    POSITIVE LOGITS
     Git
    3.29
     git
    2.82
     GitHub
    2.47
     Github
    2.27
     Docker
    2.13
    git
    2.07
     github
    1.92
     docker
    1.75
     npm
    1.74
    docker
    1.65
    Activations Density 0.049%

    No Known Activations