© 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. 17459
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "change" and its related forms

    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
    ngth
    -0.76
    sie
    -0.69
    esm
    -0.65
    glas
    -0.64
    PU
    -0.62
    amina
    -0.62
    tic
    -0.62
    sol
    -0.59
    imentary
    -0.58
    ractor
    -0.58
    POSITIVE LOGITS
     perceptions
    1.14
     attitudes
    1.03
     minds
    0.97
     tack
    0.95
     course
    0.94
     diapers
    0.93
     gears
    0.91
     direction
    0.89
     perception
    0.87
     hearts
    0.84
    Activations Density 0.056%

    No Known Activations