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. 1-RES-JB
    6. 11764
    Prev
    Next
    INDEX
    Explanations

    Roman and Greek letters and mathematical symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly the letter 'Î'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.82
    ITNESS
    -0.79
    ilage
    -0.78
    eele
    -0.74
     Johnston
    -0.70
     Keen
    -0.66
    igun
    -0.66
    ividual
    -0.65
    PsyNetMessage
    -0.64
     Rapp
    -0.64
    POSITIVE LOGITS
    Î
    1.32
    Ķ
    1.27
    ¸
    1.26
    ©
    1.23
    ´
    1.18
    Ł
    1.18
    ©¶æ¥µ
    1.12
    ¯
    1.10
    ¶
    1.09
    ¹
    1.06
    Activations Density 0.006%

    No Known Activations