© 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. 7-RES-JB
    11. 1661
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Jeremy."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jeremy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.85
    ional
    -0.85
    pmwiki
    -0.83
    agra
    -0.79
    holders
    -0.78
    ship
    -0.71
    ledged
    -0.71
    liness
    -0.70
    sites
    -0.70
    hips
    -0.70
    POSITIVE LOGITS
     Corbyn
    1.27
     Clarkson
    0.98
     Hammond
    0.96
     Davidson
    0.85
    urger
    0.83
    IELD
    0.81
     Bent
    0.80
     Pax
    0.78
     Peters
    0.75
     Sanchez
    0.74
    Activations Density 0.021%

    No Known Activations