© 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. 3-RES-JB
    11. 3914
    Prev
    Next
    INDEX
    Explanations

    references to the weapon "Taser"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of tasers and their use in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erest
    -0.94
    orio
    -0.86
    orno
    -0.81
    ordan
    -0.77
    estine
    -0.74
    ORED
    -0.69
    ALE
    -0.65
     Granger
    -0.64
    ourn
    -0.64
    ppo
    -0.64
    POSITIVE LOGITS
    aser
    0.83
    bang
    0.77
    atis
    0.72
     choke
    0.71
    asers
    0.70
     Runner
    0.70
    bomb
    0.69
     salute
    0.69
     turrets
    0.69
     Frontier
    0.68
    Activations Density 0.006%

    No Known Activations