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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 38
    Prev
    Next
    INDEX
    Explanations

    numerical values resembling permits, approvals, or rankings

    oai_token-act-pair · gpt-3.5-turbo

    the presence of numeric values

    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
     istg
    -0.70
     lemon
    -0.65
     hopes
    -0.63
     thumbs
    -0.63
     bas
    -0.61
     retired
    -0.60
     Pixie
    -0.58
    rette
    -0.57
     biography
    -0.57
    ãĤ©
    -0.56
    POSITIVE LOGITS
    11
    3.18
    12
    2.28
    13
    2.15
    10
    2.12
    14
    2.02
    15
    1.96
    16
    1.96
    17
    1.95
    21
    1.91
    22
    1.86
    Activations Density 0.020%

    No Known Activations