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. 8-RES-JB
    6. 16310
    Prev
    Next
    INDEX
    Explanations

    internet URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and links contained within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eday
    -0.64
     ¶
    -0.62
     Takeru
    -0.60
     multiplication
    -0.59
     Ryu
    -0.59
     outweigh
    -0.59
     withdrawn
    -0.58
     aging
    -0.58
     Lab
    -0.57
     reject
    -0.57
    POSITIVE LOGITS
    www
    1.44
    imgur
    1.20
    youtu
    1.14
    twitter
    1.11
    tv
    0.99
    goo
    0.96
    forum
    0.96
    ://
    0.95
    archive
    0.94
    redd
    0.94
    Activations Density 0.017%

    No Known Activations