© 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. 0-RES-JB
    11. 392
    Prev
    Next
    INDEX
    Explanations

    instances of actions being accompanied by someone or something

    oai_token-act-pair · gpt-3.5-turbo

    the word "accompanied" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Profit
    -0.68
    gest
    -0.68
     grid
    -0.63
     Grid
    -0.62
    profit
    -0.61
     Point
    -0.60
     Silicon
    -0.60
    need
    -0.59
     eth
    -0.57
     waste
    -0.56
    POSITIVE LOGITS
     accompanied
    3.80
     accompanies
    2.53
     preceded
    2.19
     accompany
    2.19
    accompanied
    2.04
     accomp
    1.68
     followed
    1.68
     accompanying
    1.65
     greeted
    1.62
     flanked
    1.58
    Activations Density 0.013%

    No Known Activations