© 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. 0-RES-JB
    11. 8228
    Prev
    Next
    INDEX
    Explanations

    words related to the Miami Heat basketball team

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Heat," specifically related to the Miami Heat basketball team

    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
    interstitial
    -0.74
    DD
    -0.67
    PT
    -0.67
     puppet
    -0.66
    ng
    -0.65
     deserted
    -0.64
    lé
    -0.63
     viol
    -0.62
    uary
    -0.61
     vag
    -0.60
    POSITIVE LOGITS
     Heat
    3.90
    Heat
    2.98
    heat
    1.96
     heat
    1.93
     Hurricanes
    1.55
     Bosh
    1.52
     Flames
    1.50
     Dolphins
    1.43
     heats
    1.43
     Pistons
    1.41
    Activations Density 0.015%

    No Known Activations