© 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. 3-RES-JB
    11. 18561
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Boy" or related phrases like "Boycott" and "Boycott" which are repeated across the text snippets

    oai_token-act-pair · gpt-3.5-turbo

    references to a group or entity related to the term "Boycott."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -1.20
    aukee
    -0.89
     podium
    -0.80
    insula
    -0.74
    ickr
    -0.74
     srf
    -0.71
    ascus
    -0.71
    ocrat
    -0.69
     equilibrium
    -0.69
    andem
    -0.68
    POSITIVE LOGITS
    friend
    1.45
     Scouts
    1.25
    boy
    1.21
    cott
    1.15
    hood
    1.15
    boys
    1.15
     Scout
    1.05
     Boy
    1.04
    friends
    1.00
    Boy
    0.97
    Activations Density 0.009%

    No Known Activations