© 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. 1-RES-JB
    11. 3495
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to political figures or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.90
    wagen
    -0.86
     Sieg
    -0.79
    tons
    -0.69
    rolled
    -0.68
    strip
    -0.68
     Reson
    -0.68
     Telephone
    -0.66
    orks
    -0.66
    pter
    -0.65
    POSITIVE LOGITS
    sterdam
    0.75
     Ambrose
    0.74
    auga
    0.73
     Orig
    0.71
    afa
    0.71
    ibles
    0.70
    endi
    0.69
    qua
    0.66
    amus
    0.65
    anth
    0.65
    Activations Density 0.018%

    No Known Activations