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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 17464
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Hello."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Hello" and variations of greetings

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

    No Comments

    Negative Logits
    arian
    -0.84
    aic
    -0.77
    ipl
    -0.75
    prem
    -0.74
    arians
    -0.74
    uing
    -0.72
    rift
    -0.72
    rovers
    -0.71
    urn
    -0.70
    nutrition
    -0.70
    POSITIVE LOGITS
     Kitty
    1.03
     hello
    0.88
     Hello
    0.87
    bye
    0.80
     Goodbye
    0.80
    !.
    0.78
    !,
    0.76
     dear
    0.75
     bye
    0.74
    Hello
    0.73
    Activations Density 0.008%

    No Known Activations