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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 8830
    Prev
    Next
    INDEX
    Explanations

    governmental organizations or bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to oversight and regulatory bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.85
    anyl
    -0.84
    artist
    -0.77
    hillary
    -0.75
     differe
    -0.75
    rising
    -0.73
    depending
    -0.68
    stroke
    -0.68
     queen
    -0.68
    advertising
    -0.67
    POSITIVE LOGITS
     Act
    0.92
     Directorate
    0.90
     Fund
    0.90
     Limited
    0.86
     Ltd
    0.86
     Agency
    0.84
     Association
    0.84
    eous
    0.83
     Interface
    0.83
     Assessment
    0.82
    Activations Density 0.195%

    No Known Activations