© 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. 6-RES-JB
    11. 11679
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantity and measurement

    oai_token-act-pair · gpt-3.5-turbo

    numerical references, especially those related to quantities and timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spring
    -0.72
     Outside
    -0.72
    minster
    -0.71
    verett
    -0.67
     Ahead
    -0.66
    behind
    -0.65
     Survive
    -0.64
    iframe
    -0.64
    ppo
    -0.63
     Beyond
    -0.62
    POSITIVE LOGITS
     hundred
    0.87
     thousand
    0.81
     chars
    0.81
     kil
    0.77
    士
    0.77
     pounds
    0.72
     dozen
    0.71
     trillion
    0.70
    ÃĽ
    0.68
     hours
    0.67
    Activations Density 0.094%

    No Known Activations