© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16668
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of personal pronouns

    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
    ãĤ¤ãĥĪ
    -0.86
    ãĤ¬
    -0.76
    JV
    -0.66
    ORT
    -0.65
    Console
    -0.65
    PRES
    -0.63
    ORTS
    -0.62
     NG
    -0.61
     Alive
    -0.61
    interstitial
    -0.61
    POSITIVE LOGITS
     failed
    1.17
     departed
    1.00
     successfully
    0.97
     exited
    0.97
     completes
    0.96
     regained
    0.96
     breached
    0.95
     completed
    0.94
     botched
    0.94
     debunked
    0.93
    Activations Density 0.151%

    No Known Activations