© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9798
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically focusing on the name "Verhofstadt"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Hofstadt"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scotia
    -0.76
    ASED
    -0.69
     Marketable
    -0.66
    IVER
    -0.65
     Crush
    -0.65
     thirds
    -0.64
     Solitaire
    -0.63
     pestic
    -0.61
     à¨
    -0.60
    istically
    -0.60
    POSITIVE LOGITS
    hof
    1.31
    stadt
    1.20
    stad
    1.10
    furt
    1.05
    roth
    1.02
    enstein
    0.99
    ument
    0.96
    fur
    0.92
    mann
    0.92
    sted
    0.91
    Activations Density 0.016%

    No Known Activations