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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23546
    Prev
    Next
    INDEX
    Explanations

    Proper names and codes related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uana
    -0.83
     Vald
    -0.78
    pmwiki
    -0.77
    umat
    -0.74
    umin
    -0.74
    thumbnails
    -0.74
    Dun
    -0.74
    oké
    -0.74
    UME
    -0.74
    emis
    -0.73
    POSITIVE LOGITS
     Br
    2.64
    Br
    2.41
    br
    1.98
     br
    1.95
     BR
    1.80
    BR
    1.67
     Brus
    1.29
     Britt
    1.28
     Brittany
    1.27
     Brill
    1.22
    Activations Density 0.208%

    No Known Activations