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. 4-RES-JB
    6. 17955
    Prev
    Next
    INDEX
    Explanations

    references to data size in megabytes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of file sizes measured in megabytes (MB)

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

    No Comments

    Negative Logits
    zona
    -0.80
     abdom
    -0.71
    lict
    -0.70
     spirits
    -0.66
    uve
    -0.65
     compr
    -0.65
    angular
    -0.65
    ey
    -0.63
    theless
    -0.63
     Venus
    -0.61
    POSITIVE LOGITS
    MB
    0.86
    illion
    0.85
    utable
    0.83
    TI
    0.83
    BS
    0.82
    TPS
    0.79
    ITS
    0.78
    KB
    0.77
    TA
    0.77
    TeX
    0.76
    Activations Density 0.005%

    No Known Activations