© 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. 4-RES-JB
    11. 756
    Prev
    Next
    INDEX
    Explanations

    the word "requested", particularly in sentences where someone is asking for something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "requested" in various contexts

    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
    VERTISEMENT
    -0.81
    sam
    -0.68
    Ö
    -0.65
    mania
    -0.65
     Bom
    -0.65
    phal
    -0.65
    ìĿ
    -0.63
    mas
    -0.63
    bows
    -0.63
    son
    -0.62
    POSITIVE LOGITS
     permission
    0.82
     attendance
    0.79
     clarification
    0.78
    erville
    0.77
     pardon
    0.73
     reconsider
    0.72
     assistance
    0.72
     anonymity
    0.71
     reinforcements
    0.71
     restitution
    0.70
    Activations Density 0.053%

    No Known Activations