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

    Neuronpedia

    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. 2920
    Prev
    Next
    INDEX
    Explanations

    words related to television and media

    oai_token-act-pair · gpt-3.5-turbo

    references to television and news media

    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
    ropy
    -0.72
    staking
    -0.72
    tein
    -0.71
    maxwell
    -0.71
    imi
    -0.69
     remission
    -0.64
    rious
    -0.62
     latent
    -0.61
    etsk
    -0.61
    hirt
    -0.61
    POSITIVE LOGITS
    levision
    0.95
     VIDEOS
    0.76
     Movies
    0.75
     Channel
    0.75
     Shows
    0.75
     CLSID
    0.75
    OH
    0.74
    radio
    0.74
     telev
    0.74
    ITIES
    0.72
    Activations Density 0.338%

    No Known Activations