© 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. 2106
    Prev
    Next
    INDEX
    Explanations

    references to different countries and organizations

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to entities, particularly countries and organizations

    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
     oneself
    -0.65
    pire
    -0.64
     guiName
    -0.63
     Guan
    -0.63
     Garn
    -0.61
    owers
    -0.60
    veyard
    -0.59
    imal
    -0.59
     Gar
    -0.58
    ensor
    -0.57
    POSITIVE LOGITS
    mates
    1.65
    mate
    1.39
     mates
    1.25
     mate
    1.01
     counterparts
    0.93
    leader
    0.88
    men
    0.86
     brethren
    0.85
     motto
    0.84
     colleague
    0.81
    Activations Density 0.244%

    No Known Activations