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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 1661
    Prev
    Next
    INDEX
    Explanations

    comparative adverbs indicating a high degree or extent

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that suggest significant changes or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.87
    cius
    -0.80
    rations
    -0.74
    icipated
    -0.71
    nie
    -0.66
    rha
    -0.66
    pring
    -0.65
    lest
    -0.65
    hammad
    -0.63
    _-
    -0.62
    POSITIVE LOGITS
     vastly
    0.79
     leaps
    0.76
    UNCH
    0.76
    efully
    0.74
     illiter
    0.74
    *=-
    0.72
     discrep
    0.71
     different
    0.69
     underestimate
    0.68
    olit
    0.68
    Activations Density 0.010%

    No Known Activations