Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3038
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional relationships with food

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and speech-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilde
    -0.84
    eren
    -0.82
     Olympus
    -0.79
    OE
    -0.78
    urtles
    -0.77
    erton
    -0.77
    Bott
    -0.76
    bott
    -0.76
    orio
    -0.76
    ois
    -0.75
    POSITIVE LOGITS
     Kh
    2.41
    Kh
    2.37
     kh
    2.08
     Khan
    1.96
    kh
    1.66
     Gh
    1.59
     KH
    1.56
     Khal
    1.49
    Gh
    1.44
     Kazakh
    1.33
    Activations Density 0.195%

    No Known Activations