© 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. 3-RES-JB
    11. 17428
    Prev
    Next
    INDEX
    Explanations

    words related to physical struggle or conflict

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "gag" and related terms

    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
     Nem
    -0.62
     Scand
    -0.60
     Chau
    -0.59
     LX
    -0.58
    ONSORED
    -0.58
     Marketplace
    -0.57
     DRAG
    -0.57
     Waters
    -0.56
     Bank
    -0.55
     Annotations
    -0.55
    POSITIVE LOGITS
    omorphic
    0.65
    ided
    0.65
    otomy
    0.65
    efully
    0.64
    oots
    0.64
    sed
    0.63
    illions
    0.61
    otom
    0.61
    epad
    0.60
    antly
    0.59
    Activations Density 0.399%

    No Known Activations