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

    Neuronpedia

    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. 0-RES-JB
    11. 19200
    Prev
    Next
    INDEX
    Explanations

    company or organization abbreviations followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific organizational acronyms or governmental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pirates
    -0.80
     Ide
    -0.79
     toolbar
    -0.74
     cigarettes
    -0.70
     lottery
    -0.68
     Elections
    -0.68
     Bomb
    -0.68
    å¤
    -0.67
     iP
    -0.66
     Liberals
    -0.66
    POSITIVE LOGITS
    WR
    2.67
    stress
    1.49
    urga
    1.29
    ress
    1.21
     devote
    1.17
    uty
    1.16
    gress
    1.13
    ogle
    0.98
    eva
    0.97
    rite
    0.95
    Activations Density 0.033%

    No Known Activations