© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7070
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals in the context of sports

    oai_token-act-pair · gpt-3.5-turbo

    references to specific athletes and their performance statistics

    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
    berus
    -0.80
    uously
    -0.79
    uous
    -0.73
    izards
    -0.72
    ridor
    -0.71
    okers
    -0.70
    roll
    -0.68
    edo
    -0.68
    pelling
    -0.68
    ace
    -0.65
    POSITIVE LOGITS
    ĺħ
    0.80
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.75
     Ago
    0.71
    thood
    0.70
     preached
    0.69
    ership
    0.67
     Lama
    0.66
    ONT
    0.65
    ¶ħ
    0.65
    doms
    0.64
    Activations Density 0.045%

    No Known Activations