© 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. 3-RES-JB
    11. 9489
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering, particularly turbine engines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to turbine engines

    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
     Bunny
    -0.93
    adelphia
    -0.92
    ctr
    -0.80
     Paran
    -0.74
    NES
    -0.73
     Geo
    -0.73
     Bunker
    -0.72
    ashtra
    -0.72
     Passage
    -0.72
    Bet
    -0.71
    POSITIVE LOGITS
    lasses
    0.83
     horns
    0.79
    oping
    0.75
     jurors
    0.73
    ators
    0.72
    odes
    0.72
    anship
    0.71
    inators
    0.71
    asks
    0.70
     spins
    0.70
    Activations Density 0.000%

    No Known Activations