© 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. 2-RES-JB
    11. 21108
    Prev
    Next
    INDEX
    Explanations

    sports-related numbers and positions

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to game performance

    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
    hement
    -0.66
    romeda
    -0.61
    etsk
    -0.60
    furt
    -0.58
    odynam
    -0.56
    ktop
    -0.55
    omorphic
    -0.54
    DragonMagazine
    -0.54
    abouts
    -0.53
    uyomi
    -0.53
    POSITIVE LOGITS
    ETHOD
    0.64
    $$$$
    0.61
    75
    0.56
    :\
    0.54
     Barbarian
    0.54
     DEFENSE
    0.51
     Comments
    0.49
     à¤
    0.49
    71
    0.48
    BR
    0.48
    Activations Density 0.424%

    No Known Activations