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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 8673
    Prev
    Next
    INDEX
    Explanations

    specific mentions of television channels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various television channels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arcity
    -0.75
    ever
    -0.74
    olding
    -0.71
    enty
    -0.67
     Oilers
    -0.65
    pport
    -0.65
    gers
    -0.64
    inals
    -0.64
     sund
    -0.64
    anging
    -0.63
    POSITIVE LOGITS
     Channel
    1.06
    Channel
    1.01
     Divinity
    0.97
     channel
    0.86
    Mask
    0.82
     Tunnel
    0.81
     Islands
    0.77
     channels
    0.74
     Broadcasting
    0.73
    ombat
    0.73
    Activations Density 0.006%

    No Known Activations