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. 11-RES-JB
    6. 10018
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to sports performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.71
    jew
    -0.65
    layer
    -0.61
    mbuds
    -0.60
    wikipedia
    -0.58
     realise
    -0.57
    20439
    -0.56
    Asia
    -0.56
     ABE
    -0.55
    Ħ¢
    -0.55
    POSITIVE LOGITS
     while
    0.95
     offensively
    0.94
     averaging
    0.85
     defensively
    0.80
     despite
    0.80
     against
    0.79
     during
    0.78
     compared
    0.77
     entering
    0.76
     (.
    0.76
    Activations Density 0.145%

    No Known Activations