© 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. 9-RES-JB
    11. 1447
    Prev
    Next
    INDEX
    Explanations

    references to the use of force or weapons in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "use" in various contexts, especially regarding force and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.76
    boxing
    -0.74
    hower
    -0.69
    gradation
    -0.68
    orage
    -0.65
    llor
    -0.65
    dds
    -0.62
    ablishment
    -0.62
    rust
    -0.62
    aintain
    -0.62
    POSITIVE LOGITS
     force
    0.96
     antibiotics
    0.92
     coercive
    0.91
     coercion
    0.90
     discretion
    0.90
     pesticides
    0.87
     contraceptives
    0.86
     copyrighted
    0.83
     steroids
    0.82
     aliases
    0.82
    Activations Density 0.143%

    No Known Activations