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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1329
    Prev
    Next
    INDEX
    Explanations

    names or words with "ell" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ell."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sunscreen
    -0.72
     Social
    -0.65
     tram
    -0.65
     unpre
    -0.63
     Ãľ
    -0.63
     chronological
    -0.62
     hijab
    -0.62
     necessary
    -0.61
     mish
    -0.61
     signature
    -0.60
    POSITIVE LOGITS
    ell
    4.39
    ells
    2.50
    elling
    2.30
    eller
    2.18
    ellen
    2.10
    ELL
    2.07
    ella
    2.06
    elli
    2.00
    elled
    1.96
    elle
    1.96
    Activations Density 0.012%

    No Known Activations