© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16877
    Prev
    Next
    INDEX
    Explanations

    references to media broadcasting channels

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the SiriusXM broadcasting service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertodd
    -0.83
    ndra
    -0.79
    etsy
    -0.75
    agna
    -0.72
    ritis
    -0.71
    eric
    -0.71
    etooth
    -0.71
    closure
    -0.69
    cles
    -0.69
    llular
    -0.69
    POSITIVE LOGITS
     broadcasts
    1.35
     Broadcasting
    1.30
    TV
    1.24
     broadcasting
    1.21
     broadcaster
    1.18
     television
    1.17
     TV
    1.16
    Channel
    1.14
    Radio
    1.14
     Television
    1.13
    Activations Density 0.184%

    No Known Activations