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. 11-RES-JB
    6. 16966
    Prev
    Next
    INDEX
    Explanations

    image attribution credits related to Flickr

    oai_token-act-pair · gpt-3.5-turbo

    references to the photo-sharing platform Flickr and related Creative Commons licensing information

    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
    naires
    -0.72
    phas
    -0.66
    rums
    -0.65
    told
    -0.64
    rous
    -0.64
    ounter
    -0.63
    lesi
    -0.63
    nesia
    -0.63
    ttes
    -0.63
    verbs
    -0.63
    POSITIVE LOGITS
     Commons
    1.30
     Creative
    1.28
     commons
    1.12
    Creat
    1.04
    photos
    0.98
    Flickr
    0.96
     user
    0.94
     CC
    0.90
     Attribution
    0.88
     Flickr
    0.87
    Activations Density 0.052%

    No Known Activations