© 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. 1-RES-JB
    11. 3485
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hadiaris"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.72
     Liberty
    -0.69
     Happiness
    -0.69
    cases
    -0.63
     ATK
    -0.62
     Recover
    -0.61
     Purg
    -0.60
    take
    -0.59
     Mutual
    -0.58
    case
    -0.58
    POSITIVE LOGITS
    adi
    1.39
    akh
    0.90
    interstitial
    0.89
    ollah
    0.89
    emi
    0.88
    acan
    0.87
    obe
    0.86
    atta
    0.86
    awa
    0.86
    iatus
    0.86
    Activations Density 0.003%

    No Known Activations