© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2738
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantities or limits (e.g., "up to")

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific numerical limits or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Moving
    -0.78
    birds
    -0.74
    cat
    -0.72
    rog
    -0.68
     Cosponsors
    -0.67
    TG
    -0.67
    ãĥ¼ãĥĨ
    -0.63
    Mech
    -0.61
    Alan
    -0.61
    rollers
    -0.61
    POSITIVE LOGITS
    pload
    0.90
     date
    0.83
     200
    0.77
     3000
    0.76
     500
    0.74
     2024
    0.74
     5000
    0.73
     1500
    0.73
     2030
    0.73
    assetsadobe
    0.72
    Activations Density 0.038%

    No Known Activations