© 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. 2-RES-JB
    11. 20889
    Prev
    Next
    INDEX
    Explanations

    terms related to physical attacks or violence

    oai_token-act-pair · gpt-3.5-turbo

    references to physical assaults and related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atom
    -0.67
     CFR
    -0.66
    20439
    -0.61
    printed
    -0.61
    FORE
    -0.61
    PE
    -0.60
    ETA
    -0.60
    ocular
    -0.60
    milo
    -0.59
    cert
    -0.59
    POSITIVE LOGITS
     assault
    1.01
     assaults
    0.88
     Assault
    0.83
    assault
    0.82
    uous
    0.82
    ively
    0.79
    uously
    0.78
    ingly
    0.76
    attack
    0.75
    intosh
    0.73
    Activations Density 0.015%

    No Known Activations