© 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. 3-RES-JB
    11. 18169
    Prev
    Next
    INDEX
    Explanations

    distances measured in kilometers

    oai_token-act-pair · gpt-3.5-turbo

    references to distances measured in kilometers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tek
    -0.71
    inse
    -0.70
    udeb
    -0.68
    Management
    -0.66
    Imm
    -0.65
     Violence
    -0.65
    --+
    -0.65
     Failure
    -0.65
    ãĥīãĥ©
    -0.64
     Tata
    -0.63
    POSITIVE LOGITS
     kilometers
    1.20
     kilometres
    1.09
     km
    0.91
     miles
    0.80
     meters
    0.77
     kilomet
    0.77
    km
    0.76
    hovah
    0.75
    poons
    0.74
     metres
    0.73
    Activations Density 0.013%

    No Known Activations