© 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. 10-RES-JB
    11. 16960
    Prev
    Next
    INDEX
    Explanations

    words related to ignition or starting a process

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "spark," often in relation to inspiration, ideas, or igniting change

    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
    ographies
    -0.72
     Bastard
    -0.67
     Surv
    -0.66
    guyen
    -0.66
     cartel
    -0.65
    ordan
    -0.65
     Honour
    -0.65
     Cutler
    -0.64
     Kov
    -0.63
     hostages
    -0.63
    POSITIVE LOGITS
    plug
    1.38
    rer
    0.96
    ly
    0.95
    iously
    0.95
    lights
    0.91
    lins
    0.90
    ler
    0.90
    le
    0.89
    lers
    0.89
    Fun
    0.89
    Activations Density 0.057%

    No Known Activations