© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10953
    Prev
    Next
    INDEX
    Explanations

    references to incidents involving physical injuries

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals who have been injured or harmed

    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
    perm
    -0.80
    ordan
    -0.78
    ramid
    -0.77
     athlet
    -0.77
     patented
    -0.73
    ð
    -0.72
    entric
    -0.71
    Ü
    -0.71
    uador
    -0.71
    opic
    -0.71
    POSITIVE LOGITS
     wounds
    0.96
     wounded
    0.95
    gun
    0.85
     wounding
    0.83
    nikov
    0.77
    lyak
    0.77
    lehem
    0.73
    bane
    0.73
     civilians
    0.73
     inflicted
    0.72
    Activations Density 0.017%

    No Known Activations