© 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. 4-RES-JB
    11. 14737
    Prev
    Next
    INDEX
    Explanations

    words related to security

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "security" in various contexts

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

    No Comments

    Negative Logits
    oric
    -0.84
    alogy
    -0.78
    ãĥ£
    -0.75
    INK
    -0.73
    ufact
    -0.70
    ohydrate
    -0.70
    luaj
    -0.70
    ced
    -0.69
     dx
    -0.69
    arget
    -0.68
    POSITIVE LOGITS
     guards
    1.10
     clearance
    0.95
     personnel
    0.95
     checkpoints
    0.88
     guard
    0.88
     security
    0.88
     checkpoint
    0.83
    Security
    0.83
     screening
    0.81
     enforcement
    0.81
    Activations Density 0.024%

    No Known Activations