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. 7-RES-JB
    6. 23285
    Prev
    Next
    INDEX
    Explanations

    phrases relating to quantity or degree, particularly emphasizing a large amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the quantity or extent of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İĭ
    -1.01
    ĺħ
    -0.79
    ĪĴ
    -0.78
    bley
    -0.75
    emen
    -0.70
    grad
    -0.70
    osen
    -0.70
    Soft
    -0.69
    Ń·
    -0.68
     Butterfly
    -0.68
    POSITIVE LOGITS
     attention
    0.72
     effort
    0.71
    antz
    0.69
     mileage
    0.68
     ado
    0.68
     bang
    0.66
     integrity
    0.66
     time
    0.66
     money
    0.66
     decomp
    0.63
    Activations Density 0.023%

    No Known Activations