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. 0-RES-JB
    6. 5982
    Prev
    Next
    INDEX
    Explanations

    mentions of different versions or types of things

    oai_token-act-pair · gpt-3.5-turbo

    the term "variant" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewater
    -0.73
    edu
    -0.69
    ecause
    -0.67
    business
    -0.66
     Emerson
    -0.66
    united
    -0.64
    apo
    -0.64
     Athletics
    -0.64
    financial
    -0.64
     Petroleum
    -0.63
    POSITIVE LOGITS
     variant
    3.46
     variants
    3.16
     Variant
    2.41
    vari
    1.87
     variation
    1.85
    Vari
    1.82
     variations
    1.72
     Vari
    1.45
     allele
    1.39
     mutation
    1.34
    Activations Density 0.017%

    No Known Activations