© 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. 8-RES-JB
    11. 4169
    Prev
    Next
    INDEX
    Explanations

    movement words related to change and growth

    oai_token-act-pair · gpt-3.5-turbo

    references to growth and change in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malaysian
    -0.64
     Lithuan
    -0.63
     Monteneg
    -0.62
     Lent
    -0.62
     reception
    -0.62
     Valentine
    -0.61
     Paran
    -0.60
     Marriott
    -0.60
     Lindsey
    -0.59
    sted
    -0.58
    POSITIVE LOGITS
    cha
    0.88
    emin
    0.80
     suddenly
    0.78
     automatically
    0.76
    Untitled
    0.73
     indistinguishable
    0.73
     crumble
    0.72
    ģ«
    0.71
     prevail
    0.70
     tremend
    0.69
    Activations Density 0.536%

    No Known Activations