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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-RES-JB
    6. 16909
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical space missions and ingredients for cooking or baking

    oai_token-act-pair · gpt-3.5-turbo

    references to the Apollo program and mentions of vanilla

    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
    wich
    -0.95
    later
    -0.84
    ering
    -0.83
    ship
    -0.79
    ividual
    -0.76
    lings
    -0.75
    igan
    -0.73
    rences
    -0.73
    ishes
    -0.73
    ishers
    -0.72
    POSITIVE LOGITS
    chio
    0.87
    urity
    0.78
    ollo
    0.74
    uracy
    0.72
    ãĥ¼ãĥĨãĤ£
    0.70
    urnal
    0.69
     Creed
    0.66
    ctic
    0.66
     Grounds
    0.66
    BILITIES
    0.66
    Activations Density 0.084%

    No Known Activations