© 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. 18294
    Prev
    Next
    INDEX
    Explanations

    words related to violent physical actions involving stabbings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stabbing incidents or attacks

    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
     Leban
    -0.73
    quickShipAvailable
    -0.70
    mberg
    -0.68
    oS
    -0.65
    XM
    -0.65
    aut
    -0.64
    uph
    -0.64
    administ
    -0.63
    VO
    -0.63
    Scot
    -0.63
    POSITIVE LOGITS
    lished
    0.99
     wounds
    0.92
     stabbed
    0.91
     stabbing
    0.89
    nesday
    0.86
     stab
    0.84
     spree
    0.81
     slit
    0.78
    lihood
    0.75
     dagger
    0.75
    Activations Density 0.015%

    No Known Activations