© 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 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. 3-RES-JB
    11. 20330
    Prev
    Next
    INDEX
    Explanations

    text indicating causation or attribution

    oai_token-act-pair · gpt-3.5-turbo

    references to causation or reasons for events

    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
     sheep
    -0.77
    adel
    -0.72
     Sheep
    -0.68
    alon
    -0.67
     jewels
    -0.66
    abbling
    -0.65
    auts
    -0.65
     scr
    -0.64
    andering
    -0.64
     sho
    -0.64
    POSITIVE LOGITS
    math
    0.79
     simultane
    0.73
     diligence
    0.73
    endment
    0.69
    */(
    0.69
     advis
    0.69
    gery
    0.67
    catentry
    0.66
    chwitz
    0.66
    gers
    0.66
    Activations Density 0.011%

    No Known Activations