© 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. 6789
    Prev
    Next
    INDEX
    Explanations

    text referring to initial processes or stages

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "initial."

    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
    rogens
    -0.78
    Sav
    -0.73
    hered
    -0.72
    yond
    -0.71
    yers
    -0.71
    romeda
    -0.70
    lov
    -0.70
    masters
    -0.68
    gemony
    -0.68
    rod
    -0.68
    POSITIVE LOGITS
     impressions
    1.04
     stages
    1.03
    izers
    0.99
     impression
    0.95
    izer
    0.95
     batch
    0.95
     reaction
    0.95
     responders
    0.92
    izations
    0.92
     phases
    0.91
    Activations Density 0.040%

    No Known Activations