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. 8-RES-JB
    6. 22169
    Prev
    Next
    INDEX
    Explanations

    percentage values and numbers related to financial figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics related to economic changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Everywhere
    -0.58
    ãģ¯
    -0.55
     alot
    -0.54
    ================
    -0.53
    ':
    -0.53
     billions
    -0.53
     wherever
    -0.53
     Guant
    -0.52
     extradition
    -0.52
     ethical
    -0.52
    POSITIVE LOGITS
    .).
    0.90
    %).
    0.82
    ).[
    0.72
     tally
    0.70
    )).
    0.69
    ).
    0.69
    )."
    0.68
    manac
    0.68
     averages
    0.67
    ulia
    0.67
    Activations Density 0.884%

    No Known Activations