© 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. 4-RES-JB
    11. 6891
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms related to different fields such as education, religion, public services, and professional activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and activism

    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
    Platform
    -0.69
    ournal
    -0.63
     Amendments
    -0.59
    phasis
    -0.55
    "},"
    -0.55
    hap
    -0.55
    clerosis
    -0.55
     Divinity
    -0.55
     Orchestra
    -0.54
     apologise
    -0.54
    POSITIVE LOGITS
    matically
    0.70
    ishly
    0.69
    tions
    0.68
     behav
    0.63
    caster
    0.62
     memor
    0.61
    ifully
    0.61
    lia
    0.61
    ically
    0.61
    fully
    0.60
    Activations Density 1.260%

    No Known Activations