© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 3406
    Prev
    Next
    INDEX
    Explanations

    mentions of gentrification

    oai_token-act-pair · gpt-3.5-turbo

    references to gentrification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.84
    Accessory
    -0.82
    aeda
    -0.80
    phrine
    -0.79
    nesota
    -0.76
    umenthal
    -0.75
    govtrack
    -0.73
    ibaba
    -0.71
    ftime
    -0.70
    braska
    -0.70
    POSITIVE LOGITS
    rification
    1.32
    rified
    1.15
    lest
    1.05
    leness
    1.03
    ility
    0.98
    rans
    0.96
    rants
    0.91
    iour
    0.89
    robe
    0.89
    rom
    0.82
    Activations Density 0.015%

    No Known Activations