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. 2-RES-JB
    6. 380
    Prev
    Next
    INDEX
    Explanations

    words that indicate multiplication or increase, typically followed by "fold"

    oai_token-act-pair · gpt-4-turbo

    instances where something is described as having increased multi-fold

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating multiplicative increases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.78
    Downloadha
    -0.75
    vae
    -0.72
    FTWARE
    -0.70
     Vital
    -0.67
    ulia
    -0.67
    vil
    -0.65
    IRO
    -0.64
    azeera
    -0.63
    vette
    -0.63
    POSITIVE LOGITS
    fold
    1.39
     fold
    1.10
    ername
    1.00
    ers
    0.83
     folded
    0.80
     Fold
    0.79
    Closure
    0.75
    clip
    0.74
     folding
    0.74
    edly
    0.71
    Activations Density 0.005%

    No Known Activations