© 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. 4-RES-JB
    11. 17376
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, particularly those named Lane

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lane" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.80
    orate
    -0.77
    ulatory
    -0.76
    rador
    -0.73
    ional
    -0.72
    ramid
    -0.71
    ority
    -0.70
    anamo
    -0.70
    raints
    -0.70
    ERAL
    -0.69
    POSITIVE LOGITS
     Lane
    1.02
    lane
    0.97
    backer
    0.76
    sey
    0.71
    ville
    0.70
    stown
    0.69
     closures
    0.68
    ige
    0.68
    holder
    0.67
    SPA
    0.66
    Activations Density 0.008%

    No Known Activations