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. 20334
    Prev
    Next
    INDEX
    Explanations

    numeric values presented with percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical percentages and statistical data related to economic 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
    hess
    -0.82
    itism
    -0.65
     luckily
    -0.64
     fortunately
    -0.63
     Shant
    -0.60
     Dance
    -0.60
    folk
    -0.60
     Mub
    -0.59
     Dino
    -0.58
    avascript
    -0.57
    POSITIVE LOGITS
     percent
    1.19
    %,
    1.16
    %
    1.15
     million
    1.11
    %.
    1.11
    %;
    0.99
     times
    0.99
    %:
    0.99
    million
    0.99
    %).
    0.96
    Activations Density 0.056%

    No Known Activations