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. 11-RES-JB
    6. 18026
    Prev
    Next
    INDEX
    Explanations

    mentions of comments and feedback, especially negative ones from the community

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing public reactions and sentiments

    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
    eria
    -0.73
    emaker
    -0.71
     berth
    -0.71
     contiguous
    -0.68
     consum
    -0.66
     decom
    -0.66
    agara
    -0.66
     consec
    -0.65
    isite
    -0.65
     completes
    -0.64
    POSITIVE LOGITS
    many
    1.25
    Others
    1.20
    some
    1.16
    Many
    1.14
     Many
    1.13
     Some
    1.13
     Lots
    1.06
    Some
    1.06
     many
    1.03
     understandably
    0.99
    Activations Density 0.545%

    No Known Activations