© 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. 10-RES-JB
    11. 6079
    Prev
    Next
    INDEX
    Explanations

    proper nouns in statements

    oai_token-act-pair · gpt-3.5-turbo

    specific character names or references in entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bilingual
    -0.70
     cler
    -0.70
     striking
    -0.69
     bottleneck
    -0.69
     annex
    -0.69
     doubling
    -0.68
     appointing
    -0.66
     constrained
    -0.66
    lihood
    -0.66
     limiting
    -0.66
    POSITIVE LOGITS
    TP
    1.09
    GN
    1.09
    &
    1.07
    TF
    1.06
    DC
    1.06
    FM
    1.05
    FS
    1.05
    BM
    1.05
    FC
    1.04
    TV
    1.03
    Activations Density 0.196%

    No Known Activations