© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20857
    Prev
    Next
    INDEX
    Explanations

    mentions of individualism or individuals in a societal or political context

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of individuality and individualism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¿
    -0.74
    ¡
    -0.69
    §
    -0.69
    common
    -0.68
    CCC
    -0.68
    ¿½
    -0.68
    forth
    -0.68
    UV
    -0.67
    veyard
    -0.67
    Ĺ
    -0.65
    POSITIVE LOGITS
    ized
    1.46
    istic
    1.34
    istically
    1.22
    ised
    1.20
    ities
    1.13
    ividual
    1.12
    ism
    1.07
    ist
    1.07
    izer
    1.02
    isations
    1.02
    Activations Density 0.044%

    No Known Activations