© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10647
    Prev
    Next
    INDEX
    Explanations

    mentions of being shot or shootings

    oai_token-act-pair · gpt-3.5-turbo

    references to shootings or instances of being shot

    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
    wcsstore
    -0.91
    DragonMagazine
    -0.88
    é¾įå¥ij士
    -0.78
    ebook
    -0.78
    é£
    -0.78
    éĸ
    -0.77
    algia
    -0.76
    Else
    -0.75
    alg
    -0.74
    Foreign
    -0.72
    POSITIVE LOGITS
    nikov
    1.01
    powder
    0.99
     shot
    0.88
    shot
    0.87
     bullets
    0.83
    gun
    0.82
     fired
    0.82
    guns
    0.78
     shots
    0.77
     revolver
    0.76
    Activations Density 0.028%

    No Known Activations