© 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. 0-RES-JB
    11. 8280
    Prev
    Next
    INDEX
    Explanations

    words related to tendencies or inclinations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating common tendencies or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wish
    -0.67
    heed
    -0.66
     grant
    -0.63
     Siem
    -0.62
     retract
    -0.61
     complete
    -0.60
    ierce
    -0.58
     susp
    -0.57
    Sir
    -0.57
     blasp
    -0.56
    POSITIVE LOGITS
     tends
    2.69
     tended
    2.30
     tending
    1.53
     varies
    1.37
    usually
    1.23
    typically
    1.22
    pmwiki
    1.21
     usually
    1.19
     prefers
    1.17
    often
    1.16
    Activations Density 0.024%

    No Known Activations