© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 13949
    Prev
    Next
    INDEX
    Explanations

    phrases related to collecting or retrieving items or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "collect" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellen
    -0.77
    ffe
    -0.71
    lihood
    -0.65
    witz
    -0.63
     substit
    -0.63
     complexion
    -0.63
    forth
    -0.63
    ned
    -0.62
     rule
    -0.61
    word
    -0.61
    POSITIVE LOGITS
    collect
    0.95
    ennial
    0.92
    ivist
    0.88
     collects
    0.88
    ibles
    0.87
    ographs
    0.86
    ilial
    0.86
    orate
    0.85
    Collect
    0.85
    ograp
    0.84
    Activations Density 0.015%

    No Known Activations