© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 3547
    Prev
    Next
    INDEX
    Explanations

    mentions of "CB" followed by a number, potentially related to a specific topic or entity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "CB" and references to military or defense contexts

    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
    lihood
    -0.76
    Magikarp
    -0.72
    wine
    -0.68
     Gamergate
    -0.64
     Gutenberg
    -0.63
     Gors
    -0.63
     UEFA
    -0.62
    umerable
    -0.62
     Voldemort
    -0.62
     Maid
    -0.60
    POSITIVE LOGITS
    oard
    0.87
    GB
    0.85
    rief
    0.84
    dar
    0.84
    STAR
    0.83
    GH
    0.78
    enzie
    0.77
     CB
    0.76
    trl
    0.75
    SA
    0.74
    Activations Density 0.006%

    No Known Activations