© 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. 15
    Prev
    Next
    INDEX
    Explanations

    words related to violent actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to serious injuries or fatalities

    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
    peg
    -0.71
    available
    -0.71
    eg
    -0.70
    urg
    -0.68
    ija
    -0.68
    û
    -0.65
    ug
    -0.64
    aign
    -0.63
    idious
    -0.62
    oha
    -0.61
    POSITIVE LOGITS
    ãĥ¥
    0.65
     Hayden
    0.64
    arts
    0.61
    theless
    0.60
     thereby
    0.59
     Ambro
    0.57
    angelo
    0.57
    arently
    0.57
     namely
    0.57
     aside
    0.55
    Activations Density 0.283%

    No Known Activations