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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15518
    Prev
    Next
    INDEX
    Explanations

    non-English characters, potentially indicating it is looking for specific languages or unique character patterns

    oai_token-act-pair · gpt-3.5-turbo

    character sequences or special characters that suggest a specific encoding or language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perse
    -0.75
     poaching
    -0.70
     livest
    -0.70
     scarce
    -0.69
     dexter
    -0.68
    comfort
    -0.65
     nutrit
    -0.64
     dipping
    -0.64
     traff
    -0.64
    Wan
    -0.64
    POSITIVE LOGITS
    ÑĮ
    1.31
    ÑĢ
    1.24
    о
    1.22
    а
    1.20
    в
    1.12
    е
    1.12
    и
    1.11
    Ñģ
    1.10
    ments
    1.08
    оÐ
    1.07
    Activations Density 0.009%

    No Known Activations