© 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. 0-RES-JB
    11. 12373
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense that indicate a change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "changed" in various contexts

    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
    bies
    -0.67
    iar
    -0.66
    onz
    -0.65
    icle
    -0.64
    athon
    -0.61
    osi
    -0.60
    inia
    -0.59
    inar
    -0.58
    iann
    -0.58
     Springer
    -0.58
    POSITIVE LOGITS
     changed
    3.32
     Changed
    2.28
    changed
    2.23
     altered
    2.09
     change
    1.92
    Changed
    1.79
     changing
    1.77
     changes
    1.75
     shifted
    1.71
     switched
    1.63
    Activations Density 0.016%

    No Known Activations