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. 10-RES-JB
    6. 8683
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "Let's"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ELD
    -0.69
     promoted
    -0.67
    eur
    -0.61
    supported
    -0.60
     Palest
    -0.59
    announced
    -0.59
     Eighth
    -0.58
     Guardian
    -0.57
    IER
    -0.57
     exhibited
    -0.56
    POSITIVE LOGITS
     summarize
    1.08
     clarify
    1.03
     pretend
    1.01
     assume
    1.01
     examine
    0.98
     simplify
    0.96
     revisit
    0.95
     recap
    0.95
     analyse
    0.94
     proceed
    0.94
    Activations Density 0.013%

    No Known Activations