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. 10-RES-JB
    6. 17957
    Prev
    Next
    INDEX
    Explanations

    mentions of gigabytes or gigabits in the context of technology or data

    oai_token-act-pair · gpt-3.5-turbo

    references to data storage and internet speed metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.73
     CONTROL
    -0.70
    ÄŁ
    -0.65
    matter
    -0.65
    tenance
    -0.63
    WAYS
    -0.60
    088
    -0.59
    UG
    -0.58
     Struggle
    -0.58
    090
    -0.58
    POSITIVE LOGITS
    abyte
    1.66
    abytes
    1.56
    abit
    1.50
    apixel
    1.29
    awatts
    1.27
    antic
    1.23
    antes
    1.19
    ante
    1.14
    antically
    1.06
    aton
    1.04
    Activations Density 0.028%

    No Known Activations