© 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. 11-RES-JB
    11. 1062
    Prev
    Next
    INDEX
    Explanations

    phrases related to measurements and quantification

    oai_token-act-pair · gpt-3.5-turbo

    negative phrases or terms related to box office performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fas
    -0.70
     Hels
    -0.69
     Samoa
    -0.66
     Territory
    -0.62
    auna
    -0.58
     Uni
    -0.58
    ãĥ»
    -0.57
     Delicious
    -0.57
     Territories
    -0.56
     Marketable
    -0.56
    POSITIVE LOGITS
    shaped
    0.97
    number
    0.93
    interstitial
    0.90
    bottom
    0.90
    archives
    0.89
    cube
    0.89
    trip
    0.89
    door
    0.88
    dating
    0.88
    sided
    0.88
    Activations Density 0.088%

    No Known Activations