© 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. 5634
    Prev
    Next
    INDEX
    Explanations

    TV channels or stations

    oai_token-act-pair · gpt-3.5-turbo

    references to television networks or broadcasts

    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
    hot
    -0.82
    cule
    -0.81
    forth
    -0.73
    20439
    -0.72
    currency
    -0.72
    abouts
    -0.71
    itudes
    -0.69
    furt
    -0.68
    rison
    -0.68
    come
    -0.68
    POSITIVE LOGITS
    ILLE
    1.25
    NZ
    0.87
    trop
    0.87
     Everywhere
    0.83
     Channel
    0.81
     Trop
    0.78
    ideo
    0.78
     Shows
    0.77
     channel
    0.76
     Broadcasting
    0.74
    Activations Density 0.048%

    No Known Activations