© 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. 4-RES-JB
    11. 105
    Prev
    Next
    INDEX
    Explanations

    words related to movie theaters or the release of movies in theaters

    oai_token-act-pair · gpt-3.5-turbo

    references to movie theaters and their operations

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

    No Comments

    Negative Logits
    eric
    -0.65
    rab
    -0.63
    tons
    -0.63
    lectic
    -0.61
     subsistence
    -0.61
    etus
    -0.61
    owder
    -0.61
     Primordial
    -0.61
    ATH
    -0.60
    de
    -0.60
    POSITIVE LOGITS
     theaters
    1.10
     Tickets
    0.79
    æ©
    0.73
     theat
    0.72
     cinem
    0.71
    çĶ°
    0.71
     marqu
    0.70
     screenings
    0.69
     satell
    0.69
    erve
    0.68
    Activations Density 0.026%

    No Known Activations