© 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. 4-RES-JB
    11. 664
    Prev
    Next
    INDEX
    Explanations

    phrases related to names

    oai_token-act-pair · gpt-3.5-turbo

    terms related to queer identity and culture

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

    No Comments

    Negative Logits
    ngth
    -0.74
    76561
    -0.66
     profession
    -0.66
    âĢ¢âĢ¢
    -0.65
     ripe
    -0.62
     slee
    -0.57
     resemb
    -0.56
    shapeshifter
    -0.56
     job
    -0.56
     iceberg
    -0.56
    POSITIVE LOGITS
    itely
    0.99
    rences
    0.88
    bush
    0.81
    ilogy
    0.78
    ocally
    0.77
    ilver
    0.74
    mire
    0.74
    ĵĺ
    0.73
    lain
    0.71
    coat
    0.71
    Activations Density 0.076%

    No Known Activations