© 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 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. 14936
    Prev
    Next
    INDEX
    Explanations

    instances where a particular action has to be done

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate obligations or requirements

    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
    âĺħ
    -0.59
    fters
    -0.58
    cade
    -0.57
    uster
    -0.56
    ibliography
    -0.55
    erno
    -0.52
    SET
    -0.51
    Newsletter
    -0.51
    ovi
    -0.51
    peed
    -0.51
    POSITIVE LOGITS
     to
    1.25
     difficulty
    1.05
     trouble
    0.97
    to
    0.96
     TO
    0.86
    To
    0.83
     recourse
    0.82
     difficulties
    0.78
     problems
    0.74
     nightmares
    0.72
    Activations Density 0.278%

    No Known Activations