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. 6-RES-JB
    6. 12517
    Prev
    Next
    INDEX
    Explanations

    words related to technology and tools

    oai_token-act-pair · gpt-3.5-turbo

    the word "uses" and its related phrases indicating functionality or application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.72
    ignt
    -0.71
    owship
    -0.70
    hood
    -0.67
    merce
    -0.66
    ocument
    -0.65
    uberty
    -0.65
    ridge
    -0.65
    stre
    -0.65
    mort
    -0.65
    POSITIVE LOGITS
    fully
    1.06
    FUL
    0.94
    fulness
    0.79
    ful
    0.78
     shortcuts
    0.72
     techniques
    0.72
    full
    0.72
     methods
    0.71
     elements
    0.70
     borrowed
    0.69
    Activations Density 0.078%

    No Known Activations