© 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. 4-RES-JB
    11. 12623
    Prev
    Next
    INDEX
    Explanations

    references to entertainment industry publications like Variety, Deadline, and The Hollywood Reporter

    oai_token-act-pair · gpt-3.5-turbo

    mentions of entertainment industry publications and sources

    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
     subsistence
    -0.74
    choes
    -0.72
    adal
    -0.70
    bands
    -0.69
    aid
    -0.66
    abases
    -0.65
    geries
    -0.65
     awoken
    -0.64
    carry
    -0.64
     peaceful
    -0.64
    POSITIVE LOGITS
     SPORTS
    0.97
     Wrap
    0.96
     Reporter
    0.94
     Pictures
    0.93
     Variety
    0.87
     Releases
    0.85
     Entertainment
    0.85
     Weekly
    0.84
     Magazine
    0.84
     WEEK
    0.79
    Activations Density 0.027%

    No Known Activations