© 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. 17460
    Prev
    Next
    INDEX
    Explanations

    terms related to appointments or assignments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to appointments and their context

    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
    OAD
    -0.92
    EEK
    -0.75
     Koen
    -0.65
    NES
    -0.64
    ITH
    -0.64
    ALD
    -0.62
     Piet
    -0.61
    uton
    -0.58
    bryce
    -0.58
    Miller
    -0.58
    POSITIVE LOGITS
    oint
    1.28
    ointed
    1.24
    ments
    1.22
    ing
    1.07
    ingly
    1.05
    eering
    0.99
    inence
    0.96
    reau
    0.93
    ement
    0.93
    ly
    0.92
    Activations Density 0.013%

    No Known Activations