© 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. 10-RES-JB
    11. 6548
    Prev
    Next
    INDEX
    Explanations

    PG<tab>10

    oai_token-act-pair · gpt-3.5-turbo

    references to "PG" (presumably "Parental Guidance") ratings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pins
    -0.78
    baugh
    -0.77
    alities
    -0.75
    ality
    -0.75
    liners
    -0.70
    perse
    -0.66
    fully
    -0.66
    bell
    -0.65
    cles
    -0.64
    ufact
    -0.64
    POSITIVE LOGITS
    omez
    0.99
    allery
    0.92
    HHHH
    0.89
    TA
    0.86
    ENC
    0.84
    roups
    0.84
    raph
    0.83
    SG
    0.81
    raphic
    0.80
    ourmet
    0.79
    Activations Density 0.055%

    No Known Activations