© 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. 8-RES-JB
    11. 16802
    Prev
    Next
    INDEX
    Explanations

    references to risking or losing one's life

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to risk or threat to life

    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
     Compliance
    -0.78
    xual
    -0.72
    RECT
    -0.71
    ERC
    -0.69
     Rect
    -0.68
    essee
    -0.67
     Celest
    -0.67
     CLSID
    -0.66
    ansion
    -0.65
    uggest
    -0.63
    POSITIVE LOGITS
    guards
    1.02
    mares
    0.94
    vich
    0.89
     endanger
    0.88
    boats
    0.88
    ffen
    0.88
    killers
    0.86
    fish
    0.84
    ously
    0.84
    saving
    0.81
    Activations Density 0.053%

    No Known Activations