© 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. 4-RES-JB
    11. 17195
    Prev
    Next
    INDEX
    Explanations

    references to television channels, particularly MTV and ITV

    oai_token-act-pair · gpt-3.5-turbo

    references to TV networks, particularly MTV and ITV

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

    No Comments

    Negative Logits
    idon
    -0.71
    sein
    -0.70
    quartered
    -0.70
    erb
    -0.68
    vere
    -0.68
     deduction
    -0.67
    built
    -0.65
    patient
    -0.64
    gged
    -0.64
     leve
    -0.64
    POSITIVE LOGITS
     MTV
    0.91
    Leaks
    0.91
     Networks
    0.90
     Advertising
    0.75
     Video
    0.73
    TV
    0.72
     Television
    0.72
     Idol
    0.72
    ision
    0.71
     Broadcasting
    0.71
    Activations Density 0.008%

    No Known Activations