© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12880
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations, particularly places with the word "York"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to geographic locations and specific publications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    sembly
    -0.62
    tones
    -0.52
    trak
    -0.52
    gaard
    -0.51
    govtrack
    -0.50
    ettlement
    -0.49
    sbm
    -0.46
     departure
    -0.46
     respectively
    -0.45
    ricular
    -0.45
    POSITIVE LOGITS
    :
    1.97
    :-
    1.55
    :(
    1.54
    :#
    1.50
    :,
    1.47
     :
    1.46
    :"
    1.44
    :'
    1.43
    :[
    1.42
    .:
    1.36
    Activations Density 0.320%

    No Known Activations