© 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. 16645
    Prev
    Next
    INDEX
    Explanations

    proper names of people and places in news articles

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names of individuals and organizations

    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
     Vict
    -0.70
     Hurricane
    -0.70
     tremend
    -0.69
     NXT
    -0.66
     RIS
    -0.65
     monog
    -0.64
     Tup
    -0.64
     Venezuelan
    -0.63
     Warehouse
    -0.63
     Destination
    -0.63
    POSITIVE LOGITS
    arkin
    0.92
    anyahu
    0.88
    acci
    0.85
    hner
    0.82
    aney
    0.82
    imore
    0.81
    espie
    0.80
    reditary
    0.79
    eger
    0.78
    essel
    0.78
    Activations Density 0.160%

    No Known Activations