© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 12490
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology companies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or entities, particularly related to media and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemat
    -0.75
     redundancy
    -0.70
     clos
    -0.70
    iances
    -0.70
    rawdownloadcloneembedreportprint
    -0.69
     aperture
    -0.68
    igating
    -0.66
    andestine
    -0.66
    utic
    -0.66
    orate
    -0.65
    POSITIVE LOGITS
    regate
    1.25
     Kong
    1.10
     Donkey
    0.99
    Boss
    0.86
    fish
    0.79
    sand
    0.79
    ombat
    0.77
    bread
    0.74
    DK
    0.74
     Bundy
    0.74
    Activations Density 0.023%

    No Known Activations