© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20864
    Prev
    Next
    INDEX
    Explanations

    references to the streaming service Netflix

    oai_token-act-pair · gpt-3.5-turbo

    references to Netflix and its content

    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
    manuel
    -0.79
    uate
    -0.78
    ften
    -0.72
    psy
    -0.71
    pell
    -0.70
    cised
    -0.69
    imer
    -0.67
     bicy
    -0.67
    tera
    -0.67
     Alz
    -0.66
    POSITIVE LOGITS
     Streaming
    0.84
    Netflix
    0.81
    Film
    0.80
     Orig
    0.80
     streaming
    0.79
    Plex
    0.77
    HQ
    0.75
     Studios
    0.75
    ®
    0.74
     Netflix
    0.74
    Activations Density 0.018%

    No Known Activations