© 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. 651
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly the name "Dennis"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dennis."

    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
    places
    -0.81
    ixed
    -0.79
    igators
    -0.79
    igation
    -0.77
    votes
    -0.71
    ixture
    -0.68
    hazard
    -0.67
    arching
    -0.66
    gary
    -0.66
    juven
    -0.66
    POSITIVE LOGITS
     Dennis
    0.87
     Rod
    0.84
     Hof
    0.78
     Garcia
    0.78
     Berg
    0.76
     Berm
    0.76
     Dixon
    0.75
     Ross
    0.74
     Mu
    0.74
     Byrne
    0.71
    Activations Density 0.008%

    No Known Activations