© 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. 2-RES-JB
    11. 24228
    Prev
    Next
    INDEX
    Explanations

    references to teenagers

    oai_token-act-pair · gpt-3.5-turbo

    references to teenagers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SHIP
    -0.75
    UTERS
    -0.67
     bilateral
    -0.66
     CODE
    -0.66
    ãģķ
    -0.63
    leased
    -0.63
    nce
    -0.63
    Luck
    -0.62
    staff
    -0.62
    fman
    -0.62
    POSITIVE LOGITS
    cape
    0.99
    uates
    0.89
    chool
    0.88
    hips
    0.83
    agers
    0.80
    paces
    0.78
    kids
    0.76
    heet
    0.76
    olesc
    0.75
    appers
    0.73
    Activations Density 0.007%

    No Known Activations