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. 17976
    Prev
    Next
    INDEX
    Explanations

    general occurrences or concepts mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "something" when discussing various topics or themes

    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
    de
    -0.84
    ped
    -0.79
    xon
    -0.76
    iday
    -0.69
    DOS
    -0.69
    mes
    -0.67
    ortex
    -0.67
    stice
    -0.67
    bda
    -0.67
    xtap
    -0.66
    POSITIVE LOGITS
     else
    1.20
     akin
    0.98
    Else
    0.93
     unheard
    0.87
     we
    0.85
     that
    0.81
     you
    0.75
     sorely
    0.75
     everyone
    0.73
     Else
    0.71
    Activations Density 0.043%

    No Known Activations