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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16718
    Prev
    Next
    INDEX
    Explanations

    words related to violent or aggressive content in cartoons

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and aggression in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -1.05
    wered
    -0.91
    grim
    -0.90
    çīĪ
    -0.83
     Sov
    -0.83
    udget
    -0.82
    thora
    -0.79
    Sov
    -0.77
    culosis
    -0.77
    aqu
    -0.77
    POSITIVE LOGITS
     cues
    1.46
     unconsciously
    1.37
     subconscious
    1.36
     behavioral
    1.35
     behaviors
    1.33
     perceptual
    1.33
     psychologists
    1.32
     cognitive
    1.31
     motivational
    1.31
     dopamine
    1.25
    Activations Density 0.678%

    No Known Activations