© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2594
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'culture'

    oai_token-act-pair · gpt-3.5-turbo

    words related to culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stopp
    -0.71
     clen
    -0.69
     ads
    -0.67
     Witnesses
    -0.67
     matches
    -0.66
     cards
    -0.66
     videos
    -0.65
     files
    -0.65
     blocks
    -0.65
     IDs
    -0.64
    POSITIVE LOGITS
    ulture
    4.42
    ultural
    2.45
    ult
    1.88
     Culture
    1.34
    culture
    1.28
    ULT
    1.26
    ulum
    1.20
    ults
    1.17
    cultural
    1.09
    lass
    1.07
    Activations Density 0.015%

    No Known Activations