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. 9-RES-JB
    6. 5175
    Prev
    Next
    INDEX
    Explanations

    web domain extensions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    busters
    -0.77
    Ö¼
    -0.72
    Grade
    -0.70
     Dempsey
    -0.67
    pring
    -0.65
     Bundy
    -0.61
     Nichols
    -0.61
     filibuster
    -0.60
     Crate
    -0.59
     Garner
    -0.59
    POSITIVE LOGITS
    /?
    1.04
    /,
    0.92
    /#
    0.89
    /-
    0.84
    /)
    0.83
    /.
    0.82
    ppe
    0.82
    tml
    0.81
    gypt
    0.77
    MpServer
    0.77
    Activations Density 0.042%

    No Known Activations