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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 17015
    Prev
    Next
    INDEX
    Explanations

    verbs related to sending or dispatching something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "send" and its variations, indicating themes of communication, dispatch, or transfer

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

    No Comments

    Negative Logits
    phe
    -0.66
    minster
    -0.63
    cube
    -0.63
    theless
    -0.63
     Lange
    -0.62
    Times
    -0.61
    Sov
    -0.60
    urity
    -0.58
     Pax
    -0.58
    vl
    -0.57
    POSITIVE LOGITS
    inel
    1.00
    imental
    0.89
    ãĥĥãĥī
    0.86
    keys
    0.82
    entious
    0.81
    irection
    0.76
    enced
    0.76
    maid
    0.75
    iments
    0.74
    itional
    0.71
    Activations Density 0.028%

    No Known Activations