Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19609
    Prev
    Next
    INDEX
    Explanations

    terms related to the Chromecast technology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of technology and brands, particularly related to the Chrome ecosystem

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osit
    -0.74
    lf
    -0.72
    riors
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.71
    ld
    -0.71
    sworth
    -0.69
    lich
    -0.69
    lihood
    -0.68
    vard
    -0.68
    OPLE
    -0.68
    POSITIVE LOGITS
    wagen
    0.87
    ous
    0.70
    hops
    0.69
     sockets
    0.67
     Fiber
    0.67
    esis
    0.67
     acad
    0.66
    hou
    0.66
     cafes
    0.65
    £ı
    0.65
    Activations Density 0.055%

    No Known Activations