© 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 EvalsExportsinterp-engineNEWAPI 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. 18933
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases indicating a need for action or change

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to obligation and accountability

    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
     unlucky
    -0.67
    ãĤ¼
    -0.67
     guesses
    -0.67
     depends
    -0.65
     suggestive
    -0.65
    anticipated
    -0.65
     anticipation
    -0.65
    anka
    -0.63
     projections
    -0.62
    advant
    -0.62
    POSITIVE LOGITS
     apologize
    1.25
     cease
    1.24
     apologise
    1.23
     resign
    1.23
     stop
    1.16
     STOP
    1.15
     quit
    1.13
     rethink
    1.12
     reconsider
    1.09
     retract
    1.01
    Activations Density 0.228%

    No Known Activations