© 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. 11-RES-JB
    11. 7792
    Prev
    Next
    INDEX
    Explanations

    verbs related to learning and acquiring information

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge acquisition and information processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     broom
    -0.55
     beware
    -0.55
     perfected
    -0.54
    mare
    -0.53
    ierre
    -0.52
     mimic
    -0.51
     takeover
    -0.51
     imitate
    -0.51
     frowned
    -0.51
     retake
    -0.51
    POSITIVE LOGITS
     about
    1.13
     concerning
    1.12
     regarding
    1.10
     thus
    1.02
     anecd
    1.02
    about
    0.95
     relating
    0.91
    cerning
    0.89
     ABOUT
    0.89
     pertaining
    0.83
    Activations Density 0.229%

    No Known Activations