© 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. 1-RES-JB
    11. 11517
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant and far-reaching actions or changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate extensive or comprehensive changes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eon
    -0.71
    bia
    -0.68
    cel
    -0.68
     peg
    -0.68
    nexus
    -0.64
    xus
    -0.63
    cil
    -0.63
    mentioned
    -0.62
    rum
    -0.61
    nels
    -0.61
    POSITIVE LOGITS
    stakes
    1.21
     sweeping
    1.13
     sweep
    0.86
     sweeps
    0.86
    ãĥĥãĥĪ
    0.86
    brush
    0.79
    ãĤ£
    0.77
    ãĤĭ
    0.77
    ãĥ³ãĤ¸
    0.75
    ãĤĵ
    0.75
    Activations Density 0.005%

    No Known Activations