© 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. 1-RES-JB
    11. 21969
    Prev
    Next
    INDEX
    Explanations

    terms related to copper and copper-based materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.72
     Attribution
    -0.68
    ADRA
    -0.68
     Fundamental
    -0.68
    DEF
    -0.64
     Nobel
    -0.64
    ALE
    -0.63
    è¯
    -0.62
    URA
    -0.62
    DOM
    -0.62
    POSITIVE LOGITS
    pper
    1.37
    ppers
    1.21
    mint
    0.97
    iffe
    0.95
    ixel
    0.86
    ipher
    0.84
    xual
    0.84
    geant
    0.82
    ummer
    0.81
    icum
    0.81
    Activations Density 0.010%

    No Known Activations