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

    Neuronpedia

    Jacobian LensNEW
    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. 1007
    Prev
    Next
    INDEX
    Explanations

    historical and narrative elements in texts

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal actions and events related to individuals

    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
    hub
    -0.78
    selves
    -0.78
    aura
    -0.72
     unison
    -0.69
    eps
    -0.69
     womb
    -0.68
     husbands
    -0.66
    avia
    -0.64
    common
    -0.63
    immune
    -0.63
    POSITIVE LOGITS
     himself
    1.45
     Himself
    0.90
     his
    0.83
     personally
    0.64
    panic
    0.64
     subordinates
    0.63
     remorse
    0.63
     wife
    0.63
     buddies
    0.62
     rall
    0.61
    Activations Density 0.818%

    No Known Activations