© 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 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. 4-RES-JB
    11. 17014
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly related to a specific person named Berger

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly in a sports context

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

    No Comments

    Negative Logits
     wrestler
    -0.68
     Huckabee
    -0.67
     Wrest
    -0.67
    ivers
    -0.67
    hander
    -0.65
    UAL
    -0.65
     Gund
    -0.65
    vision
    -0.65
    gie
    -0.64
    cess
    -0.63
    POSITIVE LOGITS
    ussen
    0.92
    olated
    0.83
     srf
    0.81
    artisan
    0.80
    onduct
    0.78
    ronics
    0.77
    hetti
    0.77
    osion
    0.76
    otle
    0.75
    9999
    0.75
    Activations Density 0.023%

    No Known Activations