© 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. 8-RES-JB
    11. 18613
    Prev
    Next
    INDEX
    Explanations

    opportunities or instances related to taking advantage of a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases and contexts related to opportunities or chances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chief
    -0.80
    ometimes
    -0.71
    Reviewed
    -0.70
    inas
    -0.70
    olphins
    -0.70
    english
    -0.70
    lisher
    -0.68
    miah
    -0.67
    raint
    -0.67
    afort
    -0.67
    POSITIVE LOGITS
    llor
    1.49
    ller
    0.86
     chance
    0.78
     Encounter
    0.77
     Rouhani
    0.76
     encounter
    0.75
    ll
    0.71
    kas
    0.71
    finder
    0.71
     Cour
    0.69
    Activations Density 0.026%

    No Known Activations