© 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. 2-RES-JB
    11. 24126
    Prev
    Next
    INDEX
    Explanations

    measurements related to distance

    oai_token-act-pair · gpt-3.5-turbo

    measurements of distance or area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bidden
    -0.83
    gotten
    -0.80
    terday
    -0.78
    tenance
    -0.76
    adobe
    -0.76
    mond
    -0.75
    stakes
    -0.74
    cipline
    -0.73
     Mothers
    -0.72
    western
    -0.71
    POSITIVE LOGITS
     km
    0.99
     kg
    0.76
     kilometers
    0.74
     kilometres
    0.73
     Cheong
    0.70
     Osw
    0.68
    dp
    0.68
    iking
    0.67
     watt
    0.65
     kWh
    0.65
    Activations Density 0.017%

    No Known Activations