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

    Neuronpedia

    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. 9-RES-JB
    11. 15460
    Prev
    Next
    INDEX
    Explanations

    similes comparing something to a specific degree or quality

    oai_token-act-pair · gpt-3.5-turbo

    similes or comparisons using "as."

    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
    authorized
    -0.62
    ricted
    -0.59
    ainer
    -0.58
     Mandatory
    -0.58
    çīĪ
    -0.58
    chnology
    -0.57
    lish
    -0.55
    landish
    -0.55
    ivals
    -0.55
    Journal
    -0.54
    POSITIVE LOGITS
     fuck
    1.07
     hell
    1.03
     heck
    0.98
    fuck
    0.97
     HELL
    0.90
    iam
    0.80
    pects
    0.78
     regards
    0.78
    pen
    0.77
     FUCK
    0.75
    Activations Density 0.096%

    No Known Activations