© 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. 2-RES-JB
    11. 2047
    Prev
    Next
    INDEX
    Explanations

    media references, especially related to movies or TV shows, and possibly some related to the Christmas season

    oai_token-act-pair · gpt-3.5-turbo

    references to popular film franchises and their associated media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     administr
    -0.89
     volunt
    -0.88
     coerc
    -0.83
     ineffective
    -0.81
    hement
    -0.80
     withdrawing
    -0.79
     ration
    -0.79
     lifes
    -0.78
     footing
    -0.78
     undet
    -0.77
    POSITIVE LOGITS
    Fans
    0.95
    Writer
    0.88
    Marvel
    0.85
    Ghost
    0.84
    Episode
    0.81
    Favorite
    0.79
    Disney
    0.79
    pmwiki
    0.78
    Music
    0.78
    NES
    0.77
    Activations Density 1.653%

    No Known Activations