© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4099
    Prev
    Next
    INDEX
    Explanations

    instances of the word "handle" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "handle."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ischer
    -0.79
    hemat
    -0.77
    mpeg
    -0.76
    esis
    -0.73
    zai
    -0.73
    oons
    -0.67
    eny
    -0.66
    oine
    -0.65
    heid
    -0.65
    adder
    -0.64
    POSITIVE LOGITS
    bars
    1.04
     responsibilities
    0.79
     paperwork
    0.76
     responsibility
    0.75
     emergencies
    0.73
     adversity
    0.72
     burdens
    0.69
     luggage
    0.69
     complaints
    0.68
     sensitive
    0.68
    Activations Density 0.047%

    No Known Activations