© 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. 17171
    Prev
    Next
    INDEX
    Explanations

    references to physical violence and assault

    oai_token-act-pair · gpt-3.5-turbo

    references to acts of violence or abuse against individuals

    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
     Siege
    -0.75
     Jump
    -0.66
    NetMessage
    -0.65
     Agriculture
    -0.62
    inelli
    -0.62
    heny
    -0.61
    icion
    -0.61
    Sund
    -0.61
    shaw
    -0.60
    vine
    -0.60
    POSITIVE LOGITS
    selves
    1.05
    self
    0.89
     unconscious
    0.85
     tremend
    0.85
    atic
    0.84
    alian
    0.80
    atically
    0.78
     uncond
    0.75
     harmless
    0.74
     aggress
    0.73
    Activations Density 0.284%

    No Known Activations