© 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. 9-RES-JB
    11. 15508
    Prev
    Next
    INDEX
    Explanations

    references to television channels and programming

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific television channels, particularly Channel 2 and Channel 1

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.72
    dden
    -0.71
     Gloria
    -0.66
    stad
    -0.61
    berman
    -0.60
     Raiders
    -0.60
    sson
    -0.59
     Linda
    -0.58
    emale
    -0.58
    ritz
    -0.58
    POSITIVE LOGITS
    washer
    0.80
    lain
    0.78
     channels
    0.77
     channel
    0.77
    ages
    0.75
    Channel
    0.74
    eval
    0.73
    voy
    0.71
     surfing
    0.68
    channel
    0.68
    Activations Density 0.046%

    No Known Activations