© 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. 1-RES-JB
    11. 14518
    Prev
    Next
    INDEX
    Explanations

    spokespersons mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespeople and their statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ech
    -0.78
    1982
    -0.67
    spir
    -0.66
    ãĤª
    -0.65
     Carbuncle
    -0.64
    avery
    -0.63
    pired
    -0.63
    awed
    -0.63
    abol
    -0.62
    ever
    -0.62
    POSITIVE LOGITS
     spokesman
    1.14
     spokeswoman
    1.00
     spokesperson
    0.96
    arten
    0.81
     Debor
    0.80
     spokes
    0.74
     glim
    0.72
     answ
    0.72
     staffer
    0.72
    orically
    0.72
    Activations Density 0.013%

    No Known Activations