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. 0-RES-JB
    6. 22845
    Prev
    Next
    INDEX
    Explanations

    words relating to communication or expression, especially emphasizing the act of conveying messages or meaning

    oai_token-act-pair · gpt-3.5-turbo

    language related to conveying messages or meanings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppo
    -0.73
     CRC
    -0.70
    udo
    -0.70
    olicy
    -0.69
    Patch
    -0.67
     Alliance
    -0.65
     Kier
    -0.65
    rance
    -0.65
    itsu
    -0.64
    BUG
    -0.64
    POSITIVE LOGITS
     convey
    3.86
     conve
    2.40
     conveyed
    2.39
     express
    1.29
     relay
    1.07
     communicate
    1.01
     communicates
    1.00
     impart
    0.98
     communicating
    0.97
     communicated
    0.96
    Activations Density 0.032%

    No Known Activations