© 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. 11-RES-JB
    11. 23807
    Prev
    Next
    INDEX
    Explanations

    time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    numeric values denoting time or duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lay
    -0.76
    loo
    -0.74
    multipl
    -0.73
    especially
    -0.71
    chwitz
    -0.70
    multiple
    -0.70
    regn
    -0.69
    raught
    -0.69
    alter
    -0.68
    ramid
    -0.67
    POSITIVE LOGITS
     cents
    1.01
     percent
    1.00
     weeks
    0.93
     minutes
    0.92
     months
    0.91
     seconds
    0.90
    %.
    0.86
     days
    0.85
     hours
    0.83
    %
    0.82
    Activations Density 0.120%

    No Known Activations