© 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. 10-RES-JB
    11. 6673
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical harm or threat of harm

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to threats and violence against individuals

    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
    atari
    -0.82
     portfolios
    -0.78
     Horizons
    -0.77
    ellen
    -0.76
     Transcript
    -0.75
     revamped
    -0.75
    soDeliveryDate
    -0.73
     Bermuda
    -0.72
     archives
    -0.72
     Kepler
    -0.70
    POSITIVE LOGITS
     violence
    1.47
    violence
    1.41
     harm
    1.32
     provocation
    1.28
     injure
    1.24
     aggression
    1.22
     robbery
    1.21
     aggress
    1.21
     violent
    1.21
     danger
    1.21
    Activations Density 0.601%

    No Known Activations