© 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. 11-RES-JB
    11. 23158
    Prev
    Next
    INDEX
    Explanations

    phrases related to sequences of actions or steps

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that indicate a sequence or connection between actions and ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anyl
    -0.67
    iew
    -0.60
    adequ
    -0.59
    hibit
    -0.58
    acea
    -0.58
    cellent
    -0.57
    ocent
    -0.57
    imates
    -0.57
    riber
    -0.56
    alse
    -0.56
    POSITIVE LOGITS
     then
    2.04
    then
    1.99
     THEN
    1.87
    Then
    1.67
     Then
    1.66
     now
    1.66
    now
    1.61
    later
    1.50
     secondly
    1.37
     later
    1.31
    Activations Density 0.438%

    No Known Activations