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. 12-RES-JB
    6. 17797
    Prev
    Next
    INDEX
    Explanations

    user experiences and opinions related to products or services

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases indicating technical issues or product reliability concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     oun
    -1.43
     eleph
    -1.37
     encount
    -1.23
     metic
    -1.23
     arrang
    -1.22
     occas
    -1.18
     trave
    -1.18
     hemor
    -1.17
     tyr
    -1.16
     tiss
    -1.15
    POSITIVE LOGITS
    Posted
    1.25
    Anonymous
    1.20
    posted
    1.16
    User
    1.10
    Registered
    1.09
    Awesome
    1.08
    Rated
    1.06
    Reply
    1.06
    Edited
    1.05
    Subject
    1.03
    Activations Density 0.129%

    No Known Activations