© 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. 2048
    Prev
    Next
    INDEX
    Explanations

    phrases related to support or opposition towards a political figure or party

    oai_token-act-pair · gpt-3.5-turbo

    references to support or assistance

    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
     NAD
    -0.66
     bulletin
    -0.61
     Spot
    -0.61
     Storage
    -0.61
     reunion
    -0.61
     tentative
    -0.60
     notebook
    -0.59
    ieu
    -0.59
     apiece
    -0.59
    glers
    -0.59
    POSITIVE LOGITS
    his
    1.30
     himself
    1.20
     his
    1.14
    His
    1.10
    Hillary
    1.09
     democr
    1.09
    him
    1.05
     Himself
    1.02
     HIS
    0.99
    TRUMP
    0.97
    Activations Density 0.697%

    No Known Activations