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. 9-RES-JB
    6. 13021
    Prev
    Next
    INDEX
    Explanations

    numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    numeric quantities, particularly those related to statistics and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.63
     brav
    -0.59
     cla
    -0.58
     grate
    -0.56
    actionDate
    -0.55
     descending
    -0.55
    channelAvailability
    -0.54
     Tob
    -0.54
     lows
    -0.53
     recognizes
    -0.53
    POSITIVE LOGITS
    ½
    1.30
    120
    1.08
    200
    1.07
    76
    1.03
    125
    1.02
    90
    0.99
     ½
    0.98
    86
    0.97
    270
    0.97
    500
    0.96
    Activations Density 0.148%

    No Known Activations