© 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. 14560
    Prev
    Next
    INDEX
    Explanations

    words related to actions of involvement or communication such as featuring, registering, or inviting

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships or actions

    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
     depended
    -0.49
     ensued
    -0.44
     ancest
    -0.43
    ersed
    -0.43
     accounted
    -0.42
     taught
    -0.42
     multiplied
    -0.41
    hops
    -0.41
     consulted
    -0.41
     cared
    -0.41
    POSITIVE LOGITS
     RTX
    0.42
    oxide
    0.40
     Wick
    0.39
    yx
    0.38
     Saturday
    0.37
     avert
    0.36
     Wednesday
    0.36
     Sunday
    0.36
     shore
    0.36
     clarify
    0.35
    Activations Density 0.885%

    No Known Activations