© 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. 1075
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rely" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "rely" and its variations, indicating dependence on something or someone

    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
    corn
    -0.76
    vision
    -0.71
    sell
    -0.70
    nick
    -0.64
    cell
    -0.64
    vals
    -0.64
    lat
    -0.63
    ugh
    -0.62
     squared
    -0.60
    education
    -0.60
    POSITIVE LOGITS
     upon
    1.01
     heavily
    0.97
     solely
    0.94
    ENCY
    0.93
    lessly
    0.92
    encies
    0.86
    enza
    0.85
    ences
    0.80
    gency
    0.78
     rely
    0.78
    Activations Density 0.027%

    No Known Activations