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. 4-RES-JB
    6. 8786
    Prev
    Next
    INDEX
    Explanations

    mentions of specific keywords in text, such as names, places, or dates

    oai_token-act-pair · gpt-3.5-turbo

    newline or paragraph break markers

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

    No Comments

    Negative Logits
     tradem
    -0.78
     reper
    -0.75
     amnesty
    -0.71
     eleph
    -0.71
    ilty
    -0.70
     exting
    -0.69
     estranged
    -0.69
     embargo
    -0.69
     theirs
    -0.68
     sovereignty
    -0.67
    POSITIVE LOGITS
    Untitled
    1.19
    CLOSE
    1.18
    WASHINGTON
    1.17
    Description
    1.17
    Abstract
    1.15
    CTV
    1.11
    Still
    1.09
    Overview
    1.09
    Trivia
    1.09
    Breaking
    1.06
    Activations Density 0.105%

    No Known Activations