© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 4262
    Prev
    Next
    INDEX
    Explanations

    words related to violent and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to homicide and extreme violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellation
    -0.83
    ellar
    -0.75
    soType
    -0.75
    bits
    -0.70
    paren
    -0.68
     misunder
    -0.67
    riched
    -0.67
    ivot
    -0.67
    BuyableInstoreAndOnline
    -0.66
     indent
    -0.66
    POSITIVE LOGITS
     spree
    1.14
     rampage
    0.86
     perpetrated
    0.85
     killings
    0.83
     victims
    0.78
    ography
    0.77
     inflicted
    0.77
     murders
    0.77
     Anonymous
    0.77
     Victims
    0.74
    Activations Density 0.191%

    No Known Activations