© 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. 7492
    Prev
    Next
    INDEX
    Explanations

    key terms or impactful elements in various contexts, such as legislation, information systems, and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    terms related to policies and regulatory frameworks

    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
    EStreamFrame
    -0.78
    é¾įå
    -0.75
    worldly
    -0.73
    $.
    -0.72
     eternity
    -0.66
    é¾įå¥ij士
    -0.65
    foreign
    -0.65
    fml
    -0.65
    ãģ¾
    -0.63
    urnal
    -0.62
    POSITIVE LOGITS
     consists
    0.88
    ariat
    0.85
     comprises
    0.77
     consisted
    0.76
     has
    0.70
     dilemma
    0.67
    undrum
    0.66
     contains
    0.66
     continues
    0.66
     provides
    0.65
    Activations Density 0.733%

    No Known Activations