© 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. 22169
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to various fields such as medicine, biology, politics, and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal 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
    arij
    -0.61
    ovie
    -0.60
    utra
    -0.58
     Carbuncle
    -0.56
    iggurat
    -0.54
    ulhu
    -0.53
    ourke
    -0.53
     lasted
    -0.52
    iphate
    -0.52
    shapeshifter
    -0.52
    POSITIVE LOGITS
     situations
    0.61
     backgrounds
    0.59
     attachments
    0.58
     levels
    0.57
     emergencies
    0.56
     calculations
    0.55
    bugs
    0.55
     margins
    0.54
     threats
    0.53
     proportions
    0.53
    Activations Density 1.444%

    No Known Activations