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. 15777
    Prev
    Next
    INDEX
    Explanations

    financial transaction amounts

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial figures

    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
     unden
    -0.87
     millenn
    -0.77
     enthusi
    -0.77
     metic
    -0.76
     behavi
    -0.75
     conflic
    -0.74
     citiz
    -0.74
     newsp
    -0.71
     mathemat
    -0.71
     proble
    -0.69
    POSITIVE LOGITS
    750
    1.54
    250
    1.54
    300
    1.51
    500
    1.51
    350
    1.50
    900
    1.48
    150
    1.47
    525
    1.45
    200
    1.45
    450
    1.44
    Activations Density 0.099%

    No Known Activations