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. 15920
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication behaviors and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest skepticism or critical thinking in various 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
     Myster
    -0.72
     Bulldogs
    -0.72
    NEY
    -0.71
    YN
    -0.70
    PB
    -0.69
    Interstitial
    -0.66
     Eth
    -0.66
     Nickel
    -0.66
     Padres
    -0.65
     Bubble
    -0.65
    POSITIVE LOGITS
    lash
    0.77
    gow
    0.77
     Shaw
    0.75
     Machina
    0.74
    ilib
    0.73
    ruck
    0.72
     crus
    0.72
    rike
    0.71
    erers
    0.71
    uit
    0.70
    Activations Density 0.267%

    No Known Activations