© 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. 8-RES-JB
    11. 6982
    Prev
    Next
    INDEX
    Explanations

    mentions of deadly or dangerous elements or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lethal weapons and their use in violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourced
    -0.93
    erous
    -0.82
    loe
    -0.75
    ourcing
    -0.74
    mbuds
    -0.73
     Username
    -0.72
    Ħ¢
    -0.72
    angelo
    -0.71
    acular
    -0.71
    ī
    -0.70
    POSITIVE LOGITS
     combination
    0.89
     reptiles
    0.88
     poison
    0.88
     weapons
    0.85
     poisonous
    0.84
     weapon
    0.84
     overdose
    0.83
     lethal
    0.83
     rays
    0.82
     pathogens
    0.82
    Activations Density 0.030%

    No Known Activations