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

    Neuronpedia

    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. 8-RES-JB
    11. 2542
    Prev
    Next
    INDEX
    Explanations

    phrases related to people arriving or being present at a location

    oai_token-act-pair · gpt-3.5-turbo

    instances of arrival or appearance

    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
    utenberg
    -0.70
    avy
    -0.68
    RH
    -0.67
    phabet
    -0.66
    tg
    -0.63
    士
    -0.63
     divisions
    -0.62
    RT
    -0.61
    dp
    -0.61
    MAT
    -0.60
    POSITIVE LOGITS
     hither
    0.85
     unexpectedly
    0.74
     doorstep
    0.73
     porch
    0.72
     downstairs
    0.71
     onstage
    0.70
     voluntarily
    0.70
     unsc
    0.69
     bluff
    0.68
     sugg
    0.68
    Activations Density 0.339%

    No Known Activations