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. 11-RES-JB
    6. 4652
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions happening or being planned

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     me
    -0.68
    ãĥĹ
    -0.61
    edit
    -0.58
    Trivia
    -0.57
    lie
    -0.57
    idy
    -0.57
    stroke
    -0.56
    idium
    -0.56
    Reilly
    -0.56
     Digest
    -0.56
    POSITIVE LOGITS
     ourselves
    2.42
     our
    1.83
     ours
    1.33
     OUR
    1.32
    Our
    1.21
     Our
    1.18
     we
    0.97
     We
    0.86
    We
    0.83
    our
    0.83
    Activations Density 0.826%

    No Known Activations