© 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. 0-RES-JB
    11. 12720
    Prev
    Next
    INDEX
    Explanations

    keywords related to distance or measurement of extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating distance or remoteness

    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
    Not in Any Lists

    No Comments

    Negative Logits
    iasis
    -0.76
    iability
    -0.64
     Introdu
    -0.61
    Subscribe
    -0.61
    ounce
    -0.61
    ancy
    -0.58
    iesel
    -0.57
     Pump
    -0.56
    cause
    -0.55
    ridge
    -0.55
    POSITIVE LOGITS
     far
    3.29
    far
    2.22
     FAR
    1.91
     Far
    1.48
     farther
    1.44
    Far
    1.43
     vastly
    1.33
     much
    1.28
     infinitely
    1.25
     furthe
    1.19
    Activations Density 0.031%

    No Known Activations