© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    statements or assertions related to opinions or arguments

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express opinions or beliefs about societal norms and responsibilities

    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
    ensed
    -0.62
    ogether
    -0.53
    daq
    -0.53
    comb
    -0.52
    eers
    -0.51
    frey
    -0.49
    stice
    -0.49
     Leban
    -0.48
     Lauder
    -0.48
    XM
    -0.48
    POSITIVE LOGITS
     atheists
    0.67
     shouldn
    0.66
     TAMADRA
    0.66
    chwitz
    0.58
     homosexuals
    0.58
     impe
    0.57
    Americans
    0.56
     Allaah
    0.56
     Jews
    0.55
     gays
    0.55
    Activations Density 0.762%

    No Known Activations