© 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. 7-RES-JB
    11. 12392
    Prev
    Next
    INDEX
    Explanations

    phrases related to education and knowledge

    oai_token-act-pair · gpt-3.5-turbo

    discussions of equality and disparities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inar
    -0.65
     Originally
    -0.64
     0004
    -0.62
    =#
    -0.62
    )"
    -0.61
     Torrent
    -0.60
     keyword
    -0.59
     pts
    -0.59
     Bulk
    -0.58
    )</
    -0.58
    POSITIVE LOGITS
    iberal
    0.75
     morally
    0.74
    annabin
    0.72
     elector
    0.66
     oneself
    0.66
    omething
    0.66
    CHQ
    0.63
    ensical
    0.63
    renheit
    0.62
     economically
    0.61
    Activations Density 1.325%

    No Known Activations