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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22884
    Prev
    Next
    INDEX
    Explanations

    information related to orders, transactions, and deadlines

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods, indicating the end of sentences

    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
     butcher
    -0.83
     lately
    -0.83
     tremend
    -0.79
     phenomen
    -0.79
     overpower
    -0.78
     painfully
    -0.76
     abduct
    -0.75
     breathing
    -0.75
     skelet
    -0.75
     abundantly
    -0.74
    POSITIVE LOGITS
     Alternatively
    1.55
     Additionally
    1.53
     Please
    1.46
     Depending
    1.45
     Each
    1.44
     If
    1.44
     Otherwise
    1.42
     Failure
    1.40
     Once
    1.39
     Upon
    1.38
    Activations Density 0.221%

    No Known Activations