© 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. 11-RES-JB
    11. 19732
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically likely names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific rank or title, particularly "Maj" (Major)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATED
    -0.70
    OTH
    -0.62
    é¾į
    -0.59
     Californ
    -0.59
    OVER
    -0.57
     heating
    -0.57
    Charges
    -0.56
     tipping
    -0.56
     Riot
    -0.55
    INESS
    -0.55
    POSITIVE LOGITS
    estic
    1.35
    ewski
    1.13
    esty
    1.00
    lis
    0.93
    adier
    0.91
    itte
    0.90
    dal
    0.89
    zinski
    0.85
    ouri
    0.83
    undai
    0.82
    Activations Density 0.034%

    No Known Activations