© 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. 6-RES-JB
    11. 22518
    Prev
    Next
    INDEX
    Explanations

    references to the name "Adrian" and possibly related topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Adrian"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rooms
    -0.84
    externalActionCode
    -0.76
    creen
    -0.75
    UV
    -0.73
     negotiator
    -0.73
    ascript
    -0.70
    FER
    -0.69
    FUL
    -0.67
    unin
    -0.67
    dayName
    -0.66
    POSITIVE LOGITS
    ovich
    0.79
    vance
    0.74
     Alvarez
    0.71
    entric
    0.71
    ité
    0.70
    mented
    0.70
    vertising
    0.69
    etics
    0.68
    oad
    0.68
    anth
    0.66
    Activations Density 0.024%

    No Known Activations