© 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. 1-RES-JB
    11. 3322
    Prev
    Next
    INDEX
    Explanations

    words related to acts of terrorism

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "terror" in various contexts related to security and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    galitarian
    -0.76
    lease
    -0.71
    endum
    -0.68
     Draper
    -0.68
    ersed
    -0.64
    ering
    -0.63
    rost
    -0.63
    through
    -0.61
     Signature
    -0.61
     Eucl
    -0.61
    POSITIVE LOGITS
     terror
    1.18
     guiActiveUn
    0.92
     prey
    0.88
     mastermind
    0.88
     wre
    0.85
     Terror
    0.84
    fully
    0.82
    istan
    0.82
     terrorist
    0.81
     menace
    0.81
    Activations Density 0.005%

    No Known Activations