© 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. 6-RES-JB
    11. 16850
    Prev
    Next
    INDEX
    Explanations

    references to the name "Victor" with varying strengths of activation

    oai_token-act-pair · gpt-3.5-turbo

    the name "Victor"

    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
    shed
    -0.80
    BOOK
    -0.76
    earance
    -0.74
    eworld
    -0.74
    eling
    -0.74
    etary
    -0.73
    dress
    -0.72
    ness
    -0.71
    lease
    -0.70
    STER
    -0.70
    POSITIVE LOGITS
     Hugo
    0.98
     Victor
    0.95
    ians
    0.87
    orian
    0.86
    ancouver
    0.85
    iana
    0.85
    inus
    0.83
     Yanuk
    0.83
    ines
    0.82
    inian
    0.82
    Activations Density 0.021%

    No Known Activations