© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of appointing or assigning roles or tasks

    oai_token-act-pair · gpt-3.5-turbo

    words related to appointments and designations

    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
    OAD
    -0.96
    EEK
    -0.78
    ε
    -0.68
    conservancy
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    ITH
    -0.61
    prototype
    -0.61
    conom
    -0.61
    ALD
    -0.60
    IGH
    -0.60
    POSITIVE LOGITS
    oint
    1.16
    ments
    1.15
    ointed
    1.15
    inence
    1.06
    ing
    1.04
    eering
    0.98
    ingly
    0.97
    rophe
    0.97
    rette
    0.96
    rive
    0.95
    Activations Density 0.011%

    No Known Activations