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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 5359
    Prev
    Next
    INDEX
    Explanations

    phrases related to education and teaching

    oai_token-act-pair · gpt-3.5-turbo

    terms related to education and informing others

    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
     Donation
    -0.63
     fav
    -0.61
     Accessed
    -0.57
     opp
    -0.57
     turf
    -0.56
     divid
    -0.56
     rapp
    -0.56
    oner
    -0.54
    imposed
    -0.53
    nit
    -0.53
    POSITIVE LOGITS
     us
    1.10
     viewers
    1.02
     readers
    1.00
     him
    0.97
    ingly
    0.97
     listeners
    0.96
     consumers
    0.91
     everyone
    0.90
    hetically
    0.87
     passers
    0.86
    Activations Density 0.312%

    No Known Activations