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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3257
    Prev
    Next
    INDEX
    Explanations

    numeric values related to prices, quantities, measurements, rankings, and percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and percentages related to financial or statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quir
    -0.68
     neighb
    -0.65
     somew
    -0.63
     exha
    -0.61
    chwitz
    -0.60
    uca
    -0.59
     rall
    -0.58
     conserv
    -0.58
     Palest
    -0.58
     cooperating
    -0.55
    POSITIVE LOGITS
     Female
    0.71
     Retrieved
    0.69
     Difference
    0.65
     [+
    0.65
     Male
    0.64
    Loading
    0.64
     [-
    0.64
    Female
    0.62
     Amount
    0.62
     Notes
    0.60
    Activations Density 0.355%

    No Known Activations