© 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. 12-RES-JB
    11. 3116
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions and interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to sounds and actions involving movement or disturbance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     behavi
    -1.07
     antioxid
    -0.96
     informing
    -0.92
     weakening
    -0.92
     withholding
    -0.91
     staging
    -0.89
     widening
    -0.89
     conclud
    -0.88
     complication
    -0.88
     disclosing
    -0.87
    POSITIVE LOGITS
    outed
    1.68
    umbled
    1.66
    ucked
    1.65
    ashed
    1.64
    ipped
    1.62
    uffed
    1.62
    agged
    1.61
    anked
    1.61
    ammed
    1.60
    anted
    1.60
    Activations Density 0.137%

    No Known Activations