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. 6507
    Prev
    Next
    INDEX
    Explanations

    keywords related to the technology company Huawei

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company Huawei and relevant technical terms

    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
    è¦ļéĨĴ
    -0.75
     Alz
    -0.75
    rely
    -0.74
    fully
    -0.73
    hold
    -0.72
    der
    -0.72
    Kings
    -0.71
    ible
    -0.71
    hist
    -0.70
    race
    -0.69
    POSITIVE LOGITS
    aries
    0.91
    awei
    0.83
     Qiao
    0.79
     quartz
    0.72
     cooker
    0.70
     cube
    0.68
    hift
    0.68
     inclined
    0.67
    ARY
    0.66
    cale
    0.66
    Activations Density 0.051%

    No Known Activations