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. 6-RES-JB
    6. 1110
    Prev
    Next
    INDEX
    Explanations

    numeric values such as measurements, percentages, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passage
    -0.66
     crowds
    -0.64
    ioch
    -0.64
     Dos
    -0.62
    ventory
    -0.61
     reperc
    -0.61
    cia
    -0.60
    atem
    -0.58
     attitude
    -0.58
     Reb
    -0.58
    POSITIVE LOGITS
    ½
    1.02
    inches
    0.81
     ½
    0.80
     inches
    0.78
    een
    0.77
    uously
    0.77
     shy
    0.76
     crore
    0.76
     cents
    0.75
     centimeters
    0.72
    Activations Density 0.137%

    No Known Activations