© 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. 10-RES-JB
    11. 18548
    Prev
    Next
    INDEX
    Explanations

    instances of verbs related to action or performance

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coup
    -0.73
     Recall
    -0.71
    iannopoulos
    -0.71
    ESE
    -0.68
     Few
    -0.68
    âĦ¢:
    -0.67
    ils
    -0.67
     Scroll
    -0.67
    xus
    -0.66
     Contains
    -0.66
    POSITIVE LOGITS
     gonna
    1.61
     going
    1.20
     trying
    1.16
     saying
    1.15
     talking
    1.12
     doing
    1.11
     kind
    1.09
     really
    1.07
     basically
    1.07
     afraid
    1.05
    Activations Density 0.347%

    No Known Activations