© 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. 11356
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for text related to clicking a box or link on a website

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "click" and its variations in the context of online interactions

    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
     Yard
    -0.67
    egal
    -0.64
    adium
    -0.64
    venge
    -0.63
     firsthand
    -0.61
     Ministers
    -0.59
     Variety
    -0.59
     ministers
    -0.57
     istg
    -0.57
     Concent
    -0.55
    POSITIVE LOGITS
    lish
    0.97
    through
    0.86
    dress
    0.79
    wheel
    0.77
    pad
    0.77
    prints
    0.75
    antry
    0.74
    urable
    0.74
    kered
    0.72
    ety
    0.72
    Activations Density 0.027%

    No Known Activations