© 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. 0-RES-JB
    11. 15085
    Prev
    Next
    INDEX
    Explanations

    words related to sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.71
     Growth
    -0.67
     Talent
    -0.66
    Population
    -0.65
    INAL
    -0.64
    IZ
    -0.63
    Comments
    -0.63
    Choice
    -0.63
    OST
    -0.63
    ostics
    -0.62
    POSITIVE LOGITS
    istor
    0.82
    rir
    0.78
    £ı
    0.77
     cris
    0.76
     aloud
    0.75
    jri
    0.74
    elsius
    0.72
    cffff
    0.72
    azeera
    0.72
    apore
    0.69
    Activations Density 0.000%

    No Known Activations