© 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. 11-RES-JB
    11. 7702
    Prev
    Next
    INDEX
    Explanations

    phrases related to cable television

    oai_token-act-pair · gpt-3.5-turbo

    references to cable television services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lori
    -0.72
    orically
    -0.72
    oric
    -0.71
     Sebastian
    -0.70
    orical
    -0.69
    ysics
    -0.66
     Sanctuary
    -0.65
    orian
    -0.65
     Herb
    -0.65
    ively
    -0.64
    POSITIVE LOGITS
     modem
    1.25
    vision
    1.03
     television
    1.01
     TV
    0.97
     cable
    0.95
     networks
    0.94
     network
    0.91
     tv
    0.86
     channels
    0.86
     Networks
    0.84
    Activations Density 0.033%

    No Known Activations