© 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. 10-RES-JB
    11. 3354
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or identities associated with individuals and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Finch
    -0.65
     Welsh
    -0.58
    ãĤ¢ãĥ«
    -0.58
    ãĤ½
    -0.58
    ãĥł
    -0.57
    mental
    -0.56
     Eleanor
    -0.56
     Beaver
    -0.55
    Cath
    -0.55
     Ecc
    -0.54
    POSITIVE LOGITS
    obin
    1.10
    chev
    0.92
    enei
    0.90
    arov
    0.87
    afi
    0.84
    src
    0.82
    ali
    0.78
    ijah
    0.77
    ¦
    0.77
    nir
    0.76
    Activations Density 0.059%

    No Known Activations