Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23004
    Prev
    Next
    INDEX
    Explanations

    phrases related to home entertainment media releases, particularly DVDs and Blu-ray Discs

    oai_token-act-pair · gpt-3.5-turbo

    references to DVD and Blu-ray releases and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onomous
    -0.88
    astical
    -0.83
    rians
    -0.78
    adow
    -0.77
    adows
    -0.72
    ndra
    -0.71
    maxwell
    -0.71
    imov
    -0.70
    unct
    -0.70
    tics
    -0.68
    POSITIVE LOGITS
     DVD
    0.99
     playback
    0.89
     cassette
    0.86
     DVDs
    0.84
     Classics
    0.84
     discs
    0.83
    Japan
    0.83
     catalogue
    0.83
     recorder
    0.82
    DVD
    0.81
    Activations Density 0.073%

    No Known Activations