Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 2462
    Prev
    Next
    INDEX
    Explanations

    mentions of historical time periods

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Back in the" followed by a year or period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Plot
    -0.69
    IUM
    -0.66
    ((
    -0.65
    Choice
    -0.65
    /#
    -0.64
    imon
    -0.64
    MON
    -0.63
    Missing
    -0.63
    MAC
    -0.63
    Express
    -0.63
    POSITIVE LOGITS
    sight
    0.81
    roads
    0.80
    animate
    0.76
    offensive
    0.76
    order
    0.74
     captivity
    0.72
     Rampage
    0.72
     heels
    0.70
    flation
    0.69
    dated
    0.66
    Activations Density 0.047%

    No Known Activations