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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23374
    Prev
    Next
    INDEX
    Explanations

    mentions of locations related to cinema, film screenings, and cinematography

    oai_token-act-pair · gpt-3.5-turbo

    references to cinema and 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
    lies
    -0.87
    nesses
    -0.85
    ional
    -0.74
    itudinal
    -0.71
    lers
    -0.68
    tnc
    -0.67
    doms
    -0.67
    lying
    -0.67
    laus
    -0.66
    le
    -0.66
    POSITIVE LOGITS
    ovies
    0.88
    goers
    0.79
     projector
    0.78
     cinem
    0.76
     premie
    0.72
     studios
    0.71
     Atmosp
    0.71
    atography
    0.71
     Kubrick
    0.70
     theaters
    0.70
    Activations Density 0.052%

    No Known Activations