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. 2-RES-JB
    6. 9979
    Prev
    Next
    INDEX
    Explanations

    times written in a particular format: hour:minute, with high emphasis on the value 10

    oai_token-act-pair · gpt-3.5-turbo

    time and date expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.99
    avorite
    -0.80
    dinand
    -0.80
    eatures
    -0.79
    yout
    -0.79
    rette
    -0.78
    undai
    -0.77
    escription
    -0.75
    etooth
    -0.75
    atown
    -0.74
    POSITIVE LOGITS
    59
    0.96
    57
    0.94
    53
    0.93
    51
    0.89
    56
    0.88
    54
    0.88
    YES
    0.87
    58
    0.87
    52
    0.84
    45
    0.80
    Activations Density 0.250%

    No Known Activations