© 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. 10-RES-JB
    11. 11260
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to knowledge or awareness

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal experiences and reflections related to emotional or moral dilemmas

    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
     Adds
    -0.60
    ggles
    -0.59
    Adds
    -0.57
     Written
    -0.55
    ebin
    -0.53
     attm
    -0.52
     Flavoring
    -0.52
     shrug
    -0.52
     Recently
    -0.52
     sigh
    -0.51
    POSITIVE LOGITS
     mattered
    1.57
     was
    1.46
     resembled
    1.45
     depended
    1.43
     belonged
    1.43
     lacked
    1.42
    was
    1.36
     seemed
    1.36
     wasn
    1.35
     amounted
    1.34
    Activations Density 1.396%

    No Known Activations