© 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. 10-RES-JB
    11. 18866
    Prev
    Next
    INDEX
    Explanations

    sentences related to politics and current events

    oai_token-act-pair · gpt-3.5-turbo

    assertions or statements of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frequ
    -0.69
    Materials
    -0.66
     Sprite
    -0.63
     thru
    -0.62
     Practices
    -0.61
     Activities
    -0.59
    Untitled
    -0.59
    pai
    -0.59
     spor
    -0.58
    Located
    -0.58
    POSITIVE LOGITS
     concede
    0.97
     reckoning
    0.95
     optimism
    0.92
     cynicism
    0.92
     vind
    0.92
     rhetorical
    0.90
     consolation
    0.90
     reasoned
    0.89
     pessim
    0.89
     Krugman
    0.89
    Activations Density 0.788%

    No Known Activations