© 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. 2-RES-JB
    11. 13770
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the status of being full or having a high quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "filled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rf
    -0.77
    hawks
    -0.75
    peer
    -0.73
    framework
    -0.68
    oa
    -0.68
    otor
    -0.68
    Friends
    -0.67
    Collins
    -0.67
    nature
    -0.66
    utan
    -0.65
    POSITIVE LOGITS
     fills
    0.88
     filled
    0.80
    fill
    0.75
     vacancies
    0.73
    ragon
    0.72
     filling
    0.71
     fill
    0.70
    filled
    0.68
    iless
    0.68
    erton
    0.67
    Activations Density 0.010%

    No Known Activations