© 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. 0-RES-JB
    11. 2935
    Prev
    Next
    INDEX
    Explanations

    words related to reviewing or rewatching content

    oai_token-act-pair · gpt-3.5-turbo

    references to replays in various contexts, particularly in sports and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mA
    -0.83
    kie
    -0.77
     Citiz
    -0.69
    Cola
    -0.69
     Milo
    -0.68
    姫
    -0.68
    rosso
    -0.68
    afort
    -0.66
     Advertisement
    -0.66
    ju
    -0.65
    POSITIVE LOGITS
     replay
    3.42
    arted
    1.57
     deposition
    1.13
    ived
    1.00
     thriller
    0.94
     Hitchcock
    0.92
     reel
    0.89
     examiner
    0.87
     helpless
    0.85
     slides
    0.81
    Activations Density 0.035%

    No Known Activations