© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 20181
    Prev
    Next
    INDEX
    Explanations

    questions or exclamations expressing surprise or confusion

    oai_token-act-pair · gpt-3.5-turbo

    questions expressing disbelief or confusion

    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
     Peninsula
    -0.68
     RC
    -0.62
    trop
    -0.60
     Discover
    -0.58
     BST
    -0.56
     Nord
    -0.56
     MAP
    -0.55
     Outdoor
    -0.55
     Interior
    -0.55
     correctly
    -0.54
    POSITIVE LOGITS
    soever
    1.34
     else
    0.87
     happ
    0.82
    ever
    0.81
     happened
    0.79
    nces
    0.78
    Cause
    0.76
     happens
    0.76
    amaz
    0.72
    ?!
    0.72
    Activations Density 0.122%

    No Known Activations