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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 10519
    Prev
    Next
    INDEX
    Explanations

    information related to global issues or the planet

    oai_token-act-pair · gpt-3.5-turbo

    references to the planet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    headers
    -0.85
    dos
    -0.78
    thumbnails
    -0.78
    inters
    -0.77
    OUT
    -0.75
    INTER
    -0.74
    DOS
    -0.73
    UCT
    -0.71
    Ô
    -0.71
    Discussion
    -0.70
    POSITIVE LOGITS
    arium
    1.17
     planet
    1.01
     Ceres
    0.98
     Earth
    0.94
    ouched
    0.93
    eers
    0.90
    wide
    0.88
    ogram
    0.86
     orbiting
    0.84
     Krypt
    0.81
    Activations Density 0.007%

    No Known Activations