© 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. 11516
    Prev
    Next
    INDEX
    Explanations

    sentences with the word "has" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "has" and its related grammatical forms

    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
    bery
    -0.68
    hand
    -0.62
    know
    -0.60
    walking
    -0.60
     knows
    -0.59
    remember
    -0.57
    iber
    -0.57
     Think
    -0.57
     Corpus
    -0.57
    TG
    -0.56
    POSITIVE LOGITS
     been
    1.30
     garnered
    1.25
    been
    1.12
     undergone
    1.08
     attracted
    1.05
     become
    1.03
     resulted
    1.03
     sparked
    1.02
     yielded
    1.00
     lasted
    0.99
    Activations Density 0.190%

    No Known Activations