© 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. 0-RES-JB
    11. 1278
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or situations that are out of the ordinary or unexpected

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "unusual" 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
    istan
    -0.73
    ware
    -0.70
    arer
    -0.68
     Step
    -0.63
    lator
    -0.63
    sold
    -0.62
    γ
    -0.62
    Free
    -0.61
    ggie
    -0.59
    ist
    -0.59
    POSITIVE LOGITS
     unusual
    3.40
     uncommon
    2.13
     unusually
    2.05
     unorthodox
    1.92
     extraordinary
    1.87
     unexpected
    1.82
     unconventional
    1.81
     anomal
    1.75
     unprecedented
    1.72
     strange
    1.67
    Activations Density 0.018%

    No Known Activations