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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9743
    Prev
    Next
    INDEX
    Explanations

    terms related to awards, recognition, and professional achievements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to awards and achievements in the entertainment industry

    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
    ĻĤ
    -0.75
    donald
    -0.71
    rising
    -0.71
     aven
    -0.70
    ischer
    -0.68
    general
    -0.67
    rez
    -0.66
    yond
    -0.65
    xious
    -0.65
     fasting
    -0.64
    POSITIVE LOGITS
     Month
    1.30
    âĦ¢
    1.28
     Award
    1.27
     Disorder
    1.26
     Agreement
    1.21
     Reduction
    1.18
     Manager
    1.17
     Units
    1.14
     Ratio
    1.13
     Mode
    1.13
    Activations Density 0.425%

    No Known Activations