© 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. 3428
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms

    oai_token-act-pair · gpt-3.5-turbo

    definite articles and related terms frequently used in legal or formal contexts

    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
    leground
    -0.80
    ceans
    -0.79
    Apps
    -0.76
    NBA
    -0.76
    hops
    -0.74
    Ops
    -0.74
    Boost
    -0.73
    AAA
    -0.72
    --+
    -0.71
    Fit
    -0.71
    POSITIVE LOGITS
     earliest
    1.50
     oldest
    1.35
     term
    1.18
    nce
    1.17
     surname
    1.13
     name
    1.12
     inscription
    1.12
     origins
    1.11
     phrase
    1.08
     youngest
    1.06
    Activations Density 0.354%

    No Known Activations