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. 10-RES-JB
    6. 10942
    Prev
    Next
    INDEX
    Explanations

    notifications, agreements, and terms related to subscribing or receiving updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subscription and consent for receiving updates or offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.57
     Blanc
    -0.46
     sim
    -0.46
    omorphic
    -0.46
     Hann
    -0.45
    ovember
    -0.44
    ewitness
    -0.44
    ccording
    -0.44
    senal
    -0.43
     brut
    -0.43
    POSITIVE LOGITS
    Subscribe
    0.59
     subscribing
    0.56
    ]);
    0.55
    ilty
    0.53
    .")
    0.53
    %).
    0.52
    ").
    0.52
    entimes
    0.51
    ');
    0.50
    ').
    0.49
    Activations Density 0.060%

    No Known Activations