© 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. 10-RES-JB
    6. 14181
    Prev
    Next
    INDEX
    Explanations

    phrases with the repetition of words

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "and" in various 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
    mer
    -0.64
     gorilla
    -0.62
    leigh
    -0.58
     Worlds
    -0.58
     Photographer
    -0.57
     Courage
    -0.57
    {"
    -0.55
    amera
    -0.55
     Fighters
    -0.55
     Jav
    -0.54
    POSITIVE LOGITS
     beyond
    0.84
    over
    0.84
    above
    0.79
     above
    0.77
     over
    0.77
     parcel
    0.70
    OTT
    0.69
    rogen
    0.68
    âķIJ
    0.66
     Beyond
    0.66
    Activations Density 0.023%

    No Known Activations