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. 0-RES-JB
    6. 7213
    Prev
    Next
    INDEX
    Explanations

    words related to notable events or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "phenomenon" and its variations

    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
     Rounds
    -0.64
    redits
    -0.63
     Bold
    -0.63
     Plans
    -0.62
    votes
    -0.62
    umber
    -0.61
    ruce
    -0.57
    ħ
    -0.57
    Email
    -0.57
    arbon
    -0.57
    POSITIVE LOGITS
     phenomenon
    3.49
     phenomena
    2.79
     sensation
    1.49
     syndrome
    1.37
     anomaly
    1.36
     phenomen
    1.32
     trend
    1.30
     pecul
    1.29
     trope
    1.28
     occurrence
    1.27
    Activations Density 0.013%

    No Known Activations