© 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. 10-RES-JB
    11. 10229
    Prev
    Next
    INDEX
    Explanations

    Italian names containing the letter combination "io"

    oai_token-act-pair · gpt-3.5-turbo

    names and proper nouns related to people

    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
    awar
    -0.74
    ipeg
    -0.73
    atively
    -0.72
    TPPStreamerBot
    -0.71
    adesh
    -0.70
    kat
    -0.70
    culosis
    -0.69
    hattan
    -0.69
    ary
    -0.68
    OWS
    -0.67
    POSITIVE LOGITS
     Rossi
    1.28
     Santos
    1.21
     Toro
    1.16
     Ferrari
    1.14
     Rivera
    1.13
    zzi
    1.13
     Silva
    1.13
     Torres
    1.12
     Alonso
    1.11
     Ronaldo
    1.10
    Activations Density 0.085%

    No Known Activations