© 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. 2567
    Prev
    Next
    INDEX
    Explanations

    Proper names, particularly the name "Dennis"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dennis" in various contexts

    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
    places
    -0.80
    igation
    -0.77
    ixed
    -0.75
    ixture
    -0.74
    votes
    -0.72
    azel
    -0.68
    igators
    -0.66
     attendant
    -0.66
    iser
    -0.64
    iliation
    -0.64
    POSITIVE LOGITS
     Dennis
    0.84
     Rod
    0.82
     Ross
    0.81
     Hof
    0.80
     Strait
    0.77
     Berg
    0.75
     Skinner
    0.73
     Roberts
    0.72
     Reed
    0.72
     Dixon
    0.71
    Activations Density 0.020%

    No Known Activations