Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5467
    Prev
    Next
    INDEX
    Explanations

    references to basketball teams and players, particularly focusing on the New York Knicks and the Boston Celtics

    oai_token-act-pair · gpt-3.5-turbo

    references to basketball teams and players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nar
    -0.69
    notations
    -0.65
    lear
    -0.64
    shore
    -0.62
     pilot
    -0.61
     scal
    -0.60
     Bore
    -0.60
     Enterprise
    -0.60
     pilots
    -0.59
     Bord
    -0.59
    POSITIVE LOGITS
    NBA
    1.00
     Basketball
    0.92
     basketball
    0.91
    asketball
    0.89
     Pacers
    0.88
    ockets
    0.87
     NBA
    0.86
     Celtics
    0.84
    adin
    0.78
     LeBron
    0.76
    Activations Density 0.177%

    No Known Activations