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. 7244
    Prev
    Next
    INDEX
    Explanations

    holiday greetings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting in text

    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
     oun
    -0.83
     stray
    -0.81
     concentrated
    -0.81
     confir
    -0.80
     extermin
    -0.79
     mutually
    -0.79
     cens
    -0.78
     fleeing
    -0.78
     unseen
    -0.78
    etheless
    -0.77
    POSITIVE LOGITS
    AMY
    1.87
    Question
    1.66
    QUEST
    1.64
    TON
    1.61
    Yeah
    1.58
    Interview
    1.58
    Q
    1.54
    KING
    1.53
    Anyway
    1.51
    BILL
    1.50
    Activations Density 0.219%

    No Known Activations