© 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. 13079
    Prev
    Next
    INDEX
    Explanations

    words related to robbery or theft

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rob."

    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
     Haf
    -0.66
     Ess
    -0.65
     anymore
    -0.64
     Dana
    -0.64
     outside
    -0.61
     ashes
    -0.61
     Mana
    -0.61
    åħī
    -0.61
     Summit
    -0.60
     intake
    -0.59
    POSITIVE LOGITS
    rob
    4.60
    robat
    2.15
    Rob
    1.72
     rob
    1.38
     Rob
    1.30
    ro
    1.28
    roph
    1.23
    roc
    1.22
    rab
    1.21
    rote
    1.17
    Activations Density 0.009%

    No Known Activations