© 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. 23551
    Prev
    Next
    INDEX
    Explanations

    words related to historical periods or eras

    oai_token-act-pair · gpt-3.5-turbo

    references to periods of time or historical contexts

    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
    ply
    -0.70
    Fly
    -0.69
    ÄŁ
    -0.66
    iants
    -0.66
    CHQ
    -0.65
    Ranked
    -0.64
    cart
    -0.64
    otle
    -0.64
    RAY
    -0.63
    birds
    -0.62
    POSITIVE LOGITS
    icals
    1.34
    icity
    1.13
    ical
    1.06
    ftime
    1.04
    ional
    0.99
     periods
    0.95
    iday
    0.88
    ically
    0.81
    isms
    0.80
    oths
    0.80
    Activations Density 0.031%

    No Known Activations