© 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. 10-RES-JB
    11. 19060
    Prev
    Next
    INDEX
    Explanations

    words related to a specific topic or entity, potentially associated with sports

    oai_token-act-pair · gpt-3.5-turbo

    references to the UK

    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
    otle
    -0.68
    OGR
    -0.64
     poppy
    -0.58
     Sina
    -0.57
     Takeru
    -0.57
    sheet
    -0.55
     Bland
    -0.55
     naïve
    -0.54
     Democr
    -0.54
    OME
    -0.54
    POSITIVE LOGITS
    ulkan
    1.50
    hov
    1.36
    umar
    1.08
    htar
    1.05
    ileaks
    1.03
    wu
    1.02
    nown
    1.00
    raine
    0.99
    won
    0.96
    unda
    0.95
    Activations Density 0.031%

    No Known Activations