© 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. 7718
    Prev
    Next
    INDEX
    Explanations

    specific time periods or deadlines mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions related to timeframes or deadlines

    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
    Ĥª
    -0.82
    OY
    -0.73
    nell
    -0.73
    dump
    -0.72
    LC
    -0.71
    Shield
    -0.69
    pict
    -0.67
    beaut
    -0.66
    oy
    -0.65
    tti
    -0.65
    POSITIVE LOGITS
     nearest
    0.97
     inception
    0.87
     receipt
    0.83
     landfall
    0.80
     completion
    0.80
     kickoff
    0.78
     offending
    0.76
     baseline
    0.74
     onset
    0.74
     shore
    0.73
    Activations Density 0.133%

    No Known Activations