© 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. 12579
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal involvement or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experience or opinions

    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
    iens
    -0.75
     Stall
    -0.73
     Definitions
    -0.72
     Emin
    -0.71
    LY
    -0.68
    xual
    -0.67
     Clover
    -0.66
     Sparkle
    -0.66
    eland
    -0.65
     Klu
    -0.65
    POSITIVE LOGITS
     identifiable
    1.21
     benefited
    0.89
     minded
    0.88
    ised
    0.87
     invested
    0.84
     offended
    0.84
     insulted
    0.80
     intervened
    0.79
     opposed
    0.78
     acquainted
    0.77
    Activations Density 0.021%

    No Known Activations