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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13457
    Prev
    Next
    INDEX
    Explanations

    words related to shooting or activities involving shooting

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "shoot" related to action or incident contexts

    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
     sentence
    -0.75
     speaker
    -0.70
     graph
    -0.68
     Meng
    -0.65
     license
    -0.63
     defendant
    -0.63
     Pay
    -0.62
     MAR
    -0.61
     pay
    -0.61
     mar
    -0.61
    POSITIVE LOGITS
    oots
    4.48
    ooting
    3.55
    oot
    2.41
    ooter
    2.19
    ooters
    1.93
    oulder
    1.55
    OTS
    1.18
    uffs
    1.13
    ooks
    1.11
    uffle
    1.11
    Activations Density 0.017%

    No Known Activations