© 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. 16623
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Genetics, particularly with 'Gen' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of genetic topics or terminology

    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
     spirited
    -0.67
     daytime
    -0.62
     form
    -0.61
     airborne
    -0.60
     podium
    -0.59
    UGH
    -0.59
    ORN
    -0.59
     leng
    -0.59
     seasonal
    -0.58
     flank
    -0.58
    POSITIVE LOGITS
    uine
    1.52
    iuses
    1.44
    ocide
    1.43
    esis
    1.24
    etically
    1.17
    omics
    1.11
    itals
    1.08
    otype
    1.07
    uin
    1.07
    etics
    1.07
    Activations Density 0.021%

    No Known Activations