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. 9-RES-JB
    6. 337
    Prev
    Next
    INDEX
    Explanations

    text surrounded by special characters and unique phrases

    oai_token-act-pair · gpt-3.5-turbo

    patterns of repeated or rhythmic sounds and sequences, particularly involving the word "ough."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.96
    stood
    -0.83
    estern
    -0.68
    raviolet
    -0.67
    namese
    -0.64
    anz
    -0.64
    lections
    -0.63
    united
    -0.63
    pedia
    -0.63
    capital
    -0.62
    POSITIVE LOGITS
    *
    2.59
    *)
    2.26
    **
    2.19
    *.
    2.14
    */
    2.07
    *,
    2.07
    *:
    1.98
     *
    1.89
    ***
    1.88
    ****
    1.82
    Activations Density 0.106%

    No Known Activations