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. 11-RES-JB
    6. 15883
    Prev
    Next
    INDEX
    Explanations

    text related to comments and discussions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "comment" and related terms

    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
    icz
    -0.74
     Sinai
    -0.73
    lay
    -0.65
     Newport
    -0.64
     Metatron
    -0.62
    YP
    -0.62
    duc
    -0.61
     Lansing
    -0.61
     abduction
    -0.60
     Eston
    -0.60
    POSITIVE LOGITS
    ariat
    1.27
    aries
    1.22
    ators
    1.00
    ature
    0.94
    arial
    0.93
     sections
    0.84
    atively
    0.83
    area
    0.82
    ator
    0.82
     threads
    0.81
    Activations Density 0.059%

    No Known Activations