© 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. 19421
    Prev
    Next
    INDEX
    Explanations

    the word "individual" or forms of it in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "individual" and its variations

    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
    late
    -0.70
    veyard
    -0.70
    GROUND
    -0.69
    lands
    -0.69
    LINE
    -0.66
    ync
    -0.66
     Dame
    -0.66
    cloth
    -0.65
    opy
    -0.65
    mosp
    -0.65
    POSITIVE LOGITS
    ized
    1.26
    istic
    1.17
    ities
    1.12
    ised
    1.01
    istically
    0.99
    isations
    0.99
    ism
    0.99
    ividual
    0.97
    izations
    0.97
    itarian
    0.97
    Activations Density 0.035%

    No Known Activations