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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11414
    Prev
    Next
    INDEX
    Explanations

    numerical values of 51 with high activations

    oai_token-act-pair · gpt-3.5-turbo

    the numerical representation of the number fifty-one 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
     Aber
    -0.65
    arily
    -0.62
    achine
    -0.62
     hypoc
    -0.61
    stic
    -0.61
    berries
    -0.60
     stemmed
    -0.60
    tainment
    -0.60
    channelAvailability
    -0.59
     eng
    -0.59
    POSITIVE LOGITS
     51
    2.72
    51
    2.06
     52
    1.68
     151
    1.50
     61
    1.46
     53
    1.46
    52
    1.44
     71
    1.42
     49
    1.41
     91
    1.37
    Activations Density 0.020%

    No Known Activations