© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9505
    Prev
    Next
    INDEX
    Explanations

    mentions of the basketball team "Washington Wizards"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Washington Wizards 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
     ore
    -0.72
    Af
    -0.72
    á
    -0.71
     mineral
    -0.71
     Gael
    -0.70
    itte
    -0.68
    ache
    -0.67
    ®
    -0.67
     unde
    -0.67
    ieu
    -0.67
    POSITIVE LOGITS
     Wizards
    3.30
     Nets
    2.12
     Rockets
    1.75
     Capitals
    1.65
     Raptors
    1.44
     Pacers
    1.37
     Cavaliers
    1.37
     Celtics
    1.36
     Bulls
    1.35
     Pistons
    1.35
    Activations Density 0.027%

    No Known Activations