© 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. 3-RES-JB
    11. 11321
    Prev
    Next
    INDEX
    Explanations

    the word 'unless'

    oai_token-act-pair · gpt-3.5-turbo

    the word "unless" and its variations, indicating conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARC
    -0.78
    ery
    -0.72
    Maker
    -0.70
    Friend
    -0.68
    eries
    -0.67
    qua
    -0.66
    Gil
    -0.64
    isible
    -0.62
    ulate
    -0.62
    sequence
    -0.61
    POSITIVE LOGITS
    soever
    1.14
     otherwise
    0.87
    fy
    0.85
    atonin
    0.69
     indemn
    0.69
    terday
    0.69
    wcsstore
    0.68
     thou
    0.67
     proxies
    0.67
    MENTS
    0.65
    Activations Density 0.010%

    No Known Activations