© 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. 17713
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of 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
    ATIONS
    -0.67
    ISION
    -0.66
    perty
    -0.63
     Pradesh
    -0.62
    ModLoader
    -0.62
     Dhabi
    -0.61
    WAYS
    -0.61
     Hirosh
    -0.61
    PDATE
    -0.61
     erection
    -0.60
    POSITIVE LOGITS
     herself
    1.05
    otte
    0.83
    thia
    0.81
     miscar
    0.81
    ova
    0.80
    rigan
    0.79
    fet
    0.78
    lette
    0.78
     bikini
    0.77
     breasts
    0.76
    Activations Density 0.254%

    No Known Activations