© 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. 0-RES-JB
    11. 4182
    Prev
    Next
    INDEX
    Explanations

    references to violence or harm, particularly related to killing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "kill."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lement
    -0.77
    ________________________
    -0.68
    ti
    -0.66
     Independence
    -0.66
    zzo
    -0.65
    stud
    -0.65
    TPPStreamerBot
    -0.65
     Poster
    -0.65
    TERN
    -0.63
    independence
    -0.62
    POSITIVE LOGITS
     kill
    3.40
     kills
    2.53
    kill
    2.41
     killing
    2.22
    Kill
    2.21
     Kill
    2.17
     killed
    2.10
     KILL
    2.03
     assassinate
    1.98
    killing
    1.92
    Activations Density 0.019%

    No Known Activations