© 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 EvalsExportsinterp-engineNEWAPI 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. 15384
    Prev
    Next
    INDEX
    Explanations

    the word "send" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "send" and its variations

    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
    ancies
    -0.73
     Catalyst
    -0.66
    ability
    -0.62
    antine
    -0.61
    mania
    -0.61
    abilities
    -0.60
     restraints
    -0.60
    models
    -0.59
     Conserv
    -0.59
    clusions
    -0.59
    POSITIVE LOGITS
     send
    3.19
    send
    2.30
     sends
    2.19
    Send
    2.13
     Send
    2.06
     sending
    2.05
     sent
    1.94
     Sending
    1.63
    sent
    1.36
     transmit
    1.31
    Activations Density 0.020%

    No Known Activations