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. 9-RES-JB
    6. 11579
    Prev
    Next
    INDEX
    Explanations

    graphics processing units (GPUs) names and models

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications related to graphics cards and their models

    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
    icity
    -0.81
    atively
    -0.80
    cially
    -0.78
    glass
    -0.75
     Debor
    -0.74
    sonian
    -0.74
    biz
    -0.72
    chy
    -0.72
    Interstitial
    -0.71
    ically
    -0.70
    POSITIVE LOGITS
     1070
    0.94
     1080
    0.87
     460
    0.86
     580
    0.86
     470
    0.82
     570
    0.82
     680
    0.81
     480
    0.80
    ĪĴ
    0.77
     760
    0.75
    Activations Density 0.059%

    No Known Activations