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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2302
    Prev
    Next
    INDEX
    Explanations

    occurrences of the number 600 followed by another number

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 600 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
    arn
    -0.75
    atto
    -0.71
    adh
    -0.67
    itch
    -0.66
    urn
    -0.66
    hedon
    -0.64
     brun
    -0.62
    æĢ
    -0.62
     Harding
    -0.61
     Anth
    -0.61
    POSITIVE LOGITS
     600
    2.75
     700
    2.22
     800
    2.13
     6000
    2.07
    600
    2.02
     400
    2.01
     900
    1.98
     1200
    1.93
     650
    1.92
     550
    1.84
    Activations Density 0.029%

    No Known Activations