Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10301
    Prev
    Next
    INDEX
    Explanations

    telephone numbers

    oai_token-act-pair · gpt-3.5-turbo

    statistical metrics related to baseball performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    SPONSORED
    -0.75
    raq
    -0.64
     metric
    -0.63
    saf
    -0.62
    oys
    -0.59
    xus
    -0.57
    obal
    -0.57
    conom
    -0.57
    mouth
    -0.56
    ters
    -0.56
    POSITIVE LOGITS
     peek
    0.56
     Deadline
    0.52
    adelphia
    0.51
     kickoff
    0.51
     progressing
    0.50
     Time
    0.50
     Catch
    0.49
    Closure
    0.49
     Break
    0.48
     Opening
    0.47
    Activations Density 0.107%

    No Known Activations