© 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. 9-RES-JB
    11. 7569
    Prev
    Next
    INDEX
    Explanations

    first-person references combined with personal opinions and observations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate personal opinions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eland
    -0.67
    Dispatch
    -0.67
     Emin
    -0.65
     Definitions
    -0.65
     Stall
    -0.64
    LY
    -0.63
     Militia
    -0.62
    ENCY
    -0.62
     Sparkle
    -0.62
     Continuous
    -0.62
    POSITIVE LOGITS
     identifiable
    1.02
     invested
    0.83
     benefited
    0.83
     intervened
    0.81
     opposed
    0.79
    ised
    0.79
     benef
    0.78
    ographed
    0.77
     attest
    0.77
     thanked
    0.76
    Activations Density 0.026%

    No Known Activations