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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 24288
    Prev
    Next
    INDEX
    Explanations

    timestamps or durations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "within" indicating timeframes or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erous
    -0.69
     inconven
    -0.69
     pointless
    -0.68
     useless
    -0.67
     silly
    -0.67
    imes
    -0.65
     antiqu
    -0.65
     screw
    -0.65
     sorry
    -0.65
     bad
    -0.64
    POSITIVE LOGITS
     Within
    3.39
    Within
    2.70
    within
    1.94
     within
    1.54
     Below
    1.45
     Upon
    1.42
     Immediately
    1.42
     Inside
    1.41
     Across
    1.34
     Among
    1.30
    Activations Density 0.014%

    No Known Activations