© 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. 17690
    Prev
    Next
    INDEX
    Explanations

    references to a specific event or organization called "CONCACAF"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names and references to CONCACAF tournaments

    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
     NCT
    -0.73
    ku
    -0.71
     Shelter
    -0.71
    itans
    -0.69
     Genie
    -0.69
     therapy
    -0.66
    Http
    -0.65
    hod
    -0.64
     empathy
    -0.63
     Illum
    -0.63
    POSITIVE LOGITS
    afort
    0.82
    ippi
    0.82
    iere
    0.78
    ĸļ
    0.78
    ansion
    0.78
    iership
    0.77
    ateg
    0.76
    noon
    0.71
    unctions
    0.71
    enaries
    0.70
    Activations Density 0.021%

    No Known Activations