© 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. 23925
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, particularly with the name "Crist" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    specific name entities, particularly proper nouns and identifiers related to individuals and places

    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
    é»Ĵ
    -0.72
    BuyableInstoreAndOnline
    -0.71
     Stras
    -0.66
     Settlement
    -0.65
     zone
    -0.64
    GAN
    -0.63
    ksh
    -0.62
     Territories
    -0.62
    FE
    -0.59
     Waste
    -0.58
    POSITIVE LOGITS
    iago
    1.10
    orian
    0.99
    oran
    0.94
    orius
    0.94
    esville
    0.93
    inho
    0.93
    rix
    0.92
    emic
    0.90
    ega
    0.90
    orial
    0.88
    Activations Density 0.106%

    No Known Activations