© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6844
    Prev
    Next
    INDEX
    Explanations

    monetary values in the form of dollars

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 400 in various contexts

    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
    •Embedding Space Digit Features

    No Comments

    Negative Logits
     jur
    -0.74
     Views
    -0.67
    icion
    -0.66
    ari
    -0.64
    Jamie
    -0.63
     Chr
    -0.62
     Jur
    -0.61
     Ryu
    -0.60
     Legisl
    -0.59
     jurors
    -0.59
    POSITIVE LOGITS
    400
    2.65
     400
    2.23
     4000
    1.53
     800
    1.48
    401
    1.43
     399
    1.42
     410
    1.39
    4000
    1.38
    500
    1.36
     405
    1.34
    Activations Density 0.025%

    No Known Activations