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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 7828
    Prev
    Next
    INDEX
    Explanations

    terms related to media playback and entertainment devices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to media playback and streaming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eanor
    -0.75
    armac
    -0.74
    ileen
    -0.73
    ean
    -0.71
    redo
    -0.71
    anthrop
    -0.68
    ila
    -0.68
    ravel
    -0.67
    ality
    -0.67
    emale
    -0.65
    POSITIVE LOGITS
     playback
    1.06
     codec
    0.91
     MPEG
    0.84
     Codec
    0.84
     clips
    0.84
     streaming
    0.82
     Roku
    0.82
     subtitles
    0.78
     streamed
    0.75
     Kodi
    0.75
    Activations Density 0.110%

    No Known Activations