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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 14012
    Prev
    Next
    INDEX
    Explanations

    nutritional information, energy upgrades, and local contractors in a program

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and comparisons in the context of discussions or arguments

    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
    webkit
    -0.76
    76561
    -0.75
     Lavrov
    -0.70
    ĸļ
    -0.69
    iii
    -0.67
    ciating
    -0.67
     vivo
    -0.64
     Cipher
    -0.62
    iPhone
    -0.61
    911
    -0.61
    POSITIVE LOGITS
     sqor
    0.82
     lows
    0.76
     Medina
    0.76
     decreases
    0.71
     Terran
    0.71
     subtract
    0.70
     backward
    0.70
     valleys
    0.68
     sellers
    0.68
     neut
    0.64
    Activations Density 0.565%

    No Known Activations