© 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. 9-RES-JB
    11. 2773
    Prev
    Next
    INDEX
    Explanations

    words related to early timing or action

    oai_token-act-pair · gpt-3.5-turbo

    the word "early" and its variations, indicating a focus on timeliness or urgency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atism
    -0.81
    ichick
    -0.74
     Canaver
    -0.72
    retched
    -0.71
    md
    -0.71
    SourceFile
    -0.70
    ittee
    -0.69
    edIn
    -0.67
    rawled
    -0.67
    atu
    -0.66
    POSITIVE LOGITS
     adop
    1.10
     morning
    0.95
     onset
    0.93
     stages
    0.92
     indications
    0.90
     mornings
    0.89
     termination
    0.86
    bird
    0.85
     arri
    0.83
     ris
    0.80
    Activations Density 0.051%

    No Known Activations