© 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. 17052
    Prev
    Next
    INDEX
    Explanations

    phrases related to timing or instances of "first time" actions

    oai_token-act-pair · gpt-3.5-turbo

    references to "first time" experiences or occurrences

    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
    inth
    -0.71
    irs
    -0.66
    rosso
    -0.65
     Journals
    -0.64
    ement
    -0.63
    addy
    -0.60
    XT
    -0.60
    irst
    -0.59
    oret
    -0.59
    ipation
    -0.58
    POSITIVE LOGITS
     round
    0.75
     encountering
    0.72
     someone
    0.71
     around
    0.70
     somebody
    0.69
     consuming
    0.69
     frame
    0.67
     earthqu
    0.62
    abl
    0.60
     bitten
    0.59
    Activations Density 0.052%

    No Known Activations