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. 6-RES-JB
    6. 23249
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Hello"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the phrase "Hello" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arian
    -0.87
    aic
    -0.81
    hip
    -0.79
    ifiable
    -0.79
    eele
    -0.78
    pite
    -0.78
    uing
    -0.78
    arians
    -0.77
    nutrition
    -0.75
    rovers
    -0.74
    POSITIVE LOGITS
     Kitty
    1.01
     hello
    0.84
     Neighbor
    0.83
    !.
    0.78
     Hello
    0.73
    !,
    0.73
     Goodbye
    0.71
     WORLD
    0.70
    !".
    0.70
    ãĥ¼ãĥ«
    0.69
    Activations Density 0.015%

    No Known Activations