© 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. 712
    Prev
    Next
    INDEX
    Explanations

    phrases related to events resulting in harm or danger to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to "casual" incidents or events

    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
     Mercury
    -0.68
     tyrann
    -0.67
     unm
    -0.66
     Centauri
    -0.64
     fluorescent
    -0.63
     prescribing
    -0.62
     questioning
    -0.62
     irrad
    -0.59
     fixation
    -0.59
     deforestation
    -0.59
    POSITIVE LOGITS
    inelli
    1.20
    imir
    1.10
    arella
    1.09
    ual
    1.08
    cas
    1.05
    itaire
    1.03
    arro
    1.03
     Royale
    1.02
    ierra
    0.97
    anova
    0.96
    Activations Density 0.012%

    No Known Activations