© 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 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. 6-RES-JB
    11. 5618
    Prev
    Next
    INDEX
    Explanations

    numerical comparisons

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "compared" related to various statistical comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recess
    -0.68
    stall
    -0.67
    acco
    -0.65
    eland
    -0.64
    authorized
    -0.63
    hold
    -0.62
    arta
    -0.61
    fruit
    -0.61
     Nebula
    -0.60
    adia
    -0.60
    POSITIVE LOGITS
     favorably
    0.93
    lihood
    0.75
    PsyNetMessage
    0.73
     guiActiveUn
    0.68
    Compare
    0.67
     objectively
    0.65
     thereto
    0.64
     Compare
    0.63
     Osw
    0.63
    bryce
    0.63
    Activations Density 0.017%

    No Known Activations