© 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 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. 6-RES-JB
    11. 2583
    Prev
    Next
    INDEX
    Explanations

    expressions related to sports events or competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive series formats in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.91
    Ń·
    -0.82
     RTX
    -0.77
     Reloaded
    -0.77
    pta
    -0.75
    ĸļ
    -0.74
     Schl
    -0.71
    uyomi
    -0.71
    anwhile
    -0.70
     plunge
    -0.66
    POSITIVE LOGITS
    sight
    0.98
    course
    0.98
    interest
    0.96
    advertising
    0.95
    arms
    0.95
    information
    0.92
    life
    0.91
    speech
    0.91
    your
    0.90
    human
    0.89
    Activations Density 0.035%

    No Known Activations