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. 7362
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a desire or preference regarding specific actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to social issues and the need for action against injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     surprisingly
    -0.70
     incorporates
    -0.68
     remarkably
    -0.67
    ciation
    -0.66
     eleg
    -0.65
    cellent
    -0.65
     admirable
    -0.65
     excellent
    -0.65
    staking
    -0.63
     Excellent
    -0.63
    POSITIVE LOGITS
     anymore
    1.65
     unnecessarily
    1.19
     ruining
    1.04
     jeopard
    1.02
     contam
    1.01
     nor
    1.01
     undue
    0.98
     tarn
    0.96
     wasted
    0.96
     wasting
    0.95
    Activations Density 0.482%

    No Known Activations