© 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. 4-RES-JB
    11. 14922
    Prev
    Next
    INDEX
    Explanations

    words related to time periods and events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific temporal periods or events

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

    No Comments

    Negative Logits
     fingerprints
    -0.74
    eers
    -0.73
    ById
    -0.71
    idis
    -0.66
     keys
    -0.64
     undone
    -0.62
    lly
    -0.61
     buttons
    -0.60
     Genie
    -0.60
    erie
    -0.58
    POSITIVE LOGITS
    panic
    0.88
    Interstitial
    0.86
    trial
    0.86
    imester
    0.78
    regnancy
    0.77
     allotted
    0.71
     periods
    0.71
     period
    0.70
     holidays
    0.67
    uncture
    0.67
    Activations Density 0.241%

    No Known Activations