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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 13529
    Prev
    Next
    INDEX
    Explanations

    mentions of the time late in the day or late in a period

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "late."

    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
    entity
    -0.71
     ILCS
    -0.70
    aves
    -0.67
    emi
    -0.66
    illion
    -0.65
    kind
    -0.63
    generated
    -0.62
     unite
    -0.62
     guiIcon
    -0.61
     certs
    -0.61
    POSITIVE LOGITS
     late
    3.58
    Late
    2.20
     early
    2.16
     Late
    2.15
    late
    1.86
     mid
    1.66
    Early
    1.53
     Early
    1.35
    early
    1.19
     earlier
    1.17
    Activations Density 0.023%

    No Known Activations