© 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. 13730
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions being taken or accepted

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" in various contexts

    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
    eers
    -0.72
     reinforcement
    -0.62
    tions
    -0.62
    glers
    -0.61
    vine
    -0.60
     SPD
    -0.60
    cers
    -0.59
    ternity
    -0.59
    ichick
    -0.57
    ileaks
    -0.56
    POSITIVE LOGITS
     aback
    1.53
     advantage
    1.10
     care
    1.07
    aways
    1.03
     seriously
    0.98
     apart
    0.91
     hostage
    0.90
     away
    0.89
     orally
    0.84
     awa
    0.82
    Activations Density 0.036%

    No Known Activations