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. 0-RES-JB
    6. 8570
    Prev
    Next
    INDEX
    Explanations

    words related to the brand "Sky"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Sky" brand or company

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollah
    -0.90
    Marx
    -0.81
     dur
    -0.79
     odor
    -0.75
     constitu
    -0.75
    tons
    -0.74
     compr
    -0.73
    olin
    -0.72
     denomin
    -0.72
    dyl
    -0.71
    POSITIVE LOGITS
     Sky
    3.83
    Sky
    3.20
     Skies
    1.83
     sky
    1.80
    sky
    1.68
     skies
    1.39
     ITV
    1.26
     SK
    1.24
     Snow
    1.21
     Sunrise
    1.18
    Activations Density 0.012%

    No Known Activations