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. 7-RES-JB
    6. 2514
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers or copyright statements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.76
     Yamato
    -0.67
    rums
    -0.67
    é¾įå¥ij士
    -0.67
     Tend
    -0.66
    cki
    -0.66
    $,
    -0.66
    abouts
    -0.62
     Towns
    -0.62
     stepping
    -0.62
    POSITIVE LOGITS
     reproduced
    0.90
     archived
    0.81
     copyrighted
    0.77
    çīĪ
    0.77
     BELOW
    0.72
    atto
    0.69
    ersed
    0.68
     expired
    0.68
     printed
    0.68
     embed
    0.67
    Activations Density 0.065%

    No Known Activations