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. 5632
    Prev
    Next
    INDEX
    Explanations

    quotes and attributions of words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to references and citations in academic or formal contexts

    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
     unlaw
    -0.73
    resa
    -0.72
    eman
    -0.64
    lyak
    -0.61
    UMP
    -0.59
    otte
    -0.58
    ittal
    -0.58
    ress
    -0.54
     GOODMAN
    -0.53
    ewitness
    -0.53
    POSITIVE LOGITS
     "â̦
    1.75
     "[
    1.71
     "...
    1.70
     "'
    1.59
     "(
    1.35
     '[
    1.29
     "
    1.25
     ".
    1.21
    "[
    1.17
     ""
    1.15
    Activations Density 0.638%

    No Known Activations