© 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. 10-RES-JB
    11. 20595
    Prev
    Next
    INDEX
    Explanations

    distances expressed in kilometers and miles

    oai_token-act-pair · gpt-3.5-turbo

    measurements of distance, particularly in kilometers and miles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defe
    -0.68
    ©¶æ
    -0.64
     precedence
    -0.61
     Schwar
    -0.58
     insecurity
    -0.57
     dissatisfaction
    -0.57
     Jinn
    -0.56
     disadvant
    -0.56
    grave
    -0.55
    aldehyde
    -0.55
    POSITIVE LOGITS
     kilometers
    1.34
    km
    1.28
     km
    1.25
     kilometres
    1.19
     miles
    1.17
     mi
    1.01
     mile
    0.95
     kilomet
    0.92
    mile
    0.91
     hectares
    0.88
    Activations Density 0.023%

    No Known Activations