Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5398
    Prev
    Next
    INDEX
    Explanations

    numbers related to amounts of money or quantities

    oai_token-act-pair · gpt-3.5-turbo

    large numerical values and measurements associated with physical properties or entities

    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
    ĪĴ
    -0.70
    ħĭ
    -0.68
     Dickinson
    -0.68
    Exit
    -0.63
    alogue
    -0.60
    ilda
    -0.59
     Cinnamon
    -0.58
     commanding
    -0.58
    aeus
    -0.58
     Nieto
    -0.58
    POSITIVE LOGITS
    pees
    0.80
    Downloadha
    0.80
    coins
    0.74
    abytes
    0.74
     pounds
    0.73
     lbs
    0.69
    acht
    0.68
    embed
    0.68
    essions
    0.67
    owment
    0.67
    Activations Density 0.232%

    No Known Activations