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. 4598
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or condemnation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that indicate relationships or comparisons

    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
     Rings
    -0.75
    agos
    -0.75
    wings
    -0.70
    °
    -0.67
     rematch
    -0.66
     Replacement
    -0.65
     Pastebin
    -0.65
    iage
    -0.64
    chwitz
    -0.64
    ages
    -0.62
    POSITIVE LOGITS
     efficiently
    1.17
    ilaterally
    1.10
     forcefully
    1.05
     violently
    1.05
     securely
    1.05
    successfully
    1.04
    ationally
    1.03
     verbally
    1.02
     smoothly
    0.99
     legally
    0.97
    Activations Density 0.170%

    No Known Activations