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. 19935
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

    oai_token-act-pair · gpt-3.5-turbo

    addresses and locations

    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
     ransom
    -0.88
    phabet
    -0.75
     regimes
    -0.74
     flavours
    -0.74
     chore
    -0.73
    ophon
    -0.71
     hurd
    -0.71
     quizz
    -0.70
     embarrass
    -0.70
     reckoning
    -0.68
    POSITIVE LOGITS
     Meadow
    1.07
     Avenue
    0.99
     Rue
    0.98
     Parkway
    0.98
     NW
    0.96
     Antioch
    0.95
     Sunset
    0.95
     Pleasant
    0.94
     Cyp
    0.92
     Avalon
    0.92
    Activations Density 0.102%

    No Known Activations