© 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. 6-RES-JB
    11. 7173
    Prev
    Next
    INDEX
    Explanations

    statements related to the initial stage or beginning of an action or process

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "initially" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rf
    -0.74
    masters
    -0.74
    gerald
    -0.70
    rom
    -0.68
    helm
    -0.66
    cig
    -0.66
     Extensions
    -0.65
     Cth
    -0.64
    laws
    -0.64
    holes
    -0.64
    POSITIVE LOGITS
     blush
    0.95
     responders
    0.89
     conceived
    0.83
     stages
    0.81
     solic
    0.78
     plotted
    0.77
     unsuccessfully
    0.75
     glance
    0.75
     teased
    0.74
     attracted
    0.74
    Activations Density 0.017%

    No Known Activations