© 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 EvalsExportsinterp-engineNEWAPI 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. 14462
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action or causing an effect

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and phrases containing it, indicating a focus on definite articles and descriptions

    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
    hips
    -0.59
     Including
    -0.55
    andise
    -0.55
    âĢİ
    -0.55
    iversity
    -0.54
    egu
    -0.54
    Ãĥ
    -0.53
    Top
    -0.51
    abel
    -0.51
    â
    -0.51
    POSITIVE LOGITS
     implication
    0.96
     narrator
    0.95
     gist
    0.87
     analogy
    0.85
     interviewer
    0.81
     reader
    0.80
     idea
    0.78
     poem
    0.77
     irony
    0.77
     protagonist
    0.75
    Activations Density 0.530%

    No Known Activations