© 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. 23085
    Prev
    Next
    INDEX
    Explanations

    mentions of movie premieres

    oai_token-act-pair · gpt-3.5-turbo

    references to premieres of shows or films

    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
    nuts
    -0.77
    agh
    -0.77
    warts
    -0.77
    surface
    -0.74
    urg
    -0.73
    otti
    -0.71
    cipl
    -0.70
    izard
    -0.69
    abul
    -0.68
    ateg
    -0.68
    POSITIVE LOGITS
     premiere
    0.93
     countdown
    0.90
     screenings
    0.89
     screening
    0.89
    éĹĺ
    0.89
     airing
    0.88
     episode
    0.87
     reel
    0.84
     premie
    0.79
     simultane
    0.77
    Activations Density 0.033%

    No Known Activations