© 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. 15905
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "Tr"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific string or sequence of characters

    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
    eers
    -0.81
    furt
    -0.80
    ãģ®éŃĶ
    -0.76
     actionGroup
    -0.74
    ELS
    -0.72
    âĸ¬âĸ¬
    -0.70
    WARE
    -0.68
    lihood
    -0.68
     Reloaded
    -0.66
    INESS
    -0.66
    POSITIVE LOGITS
    acer
    1.10
    itton
    1.10
    istan
    1.06
    ainer
    1.04
    ilateral
    1.04
    izoph
    1.02
    unn
    1.02
    icol
    1.00
    ained
    0.99
    acing
    0.98
    Activations Density 0.008%

    No Known Activations