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. 7-RES-JB
    6. 15472
    Prev
    Next
    INDEX
    Explanations

    sentences that introduce a topic or a point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the beginning of a discussion or awareness-raising post

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dissu
    -0.63
     diseng
    -0.63
     monet
    -0.63
     citizenship
    -0.62
     Io
    -0.60
     safegu
    -0.60
     away
    -0.59
     tack
    -0.59
     afar
    -0.59
     enrol
    -0.59
    POSITIVE LOGITS
    Introduction
    1.31
    Disclaimer
    1.26
    Reviewer
    1.10
    pmwiki
    1.05
    posted
    1.02
    Contents
    1.02
    Ingredients
    1.02
    TABLE
    1.01
    Chapter
    1.01
    Abstract
    0.99
    Activations Density 0.483%

    No Known Activations