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. 2023
    Prev
    Next
    INDEX
    Explanations

    keywords related to pharmaceutical investigations and legal disputes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to pharmaceutical investigations and regulatory processes

    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
     someday
    -1.04
    America
    -1.02
     civilizations
    -0.93
     civilization
    -0.89
    colored
    -0.88
    American
    -0.88
    Americans
    -0.85
     badass
    -0.83
    avored
    -0.82
     honored
    -0.81
    POSITIVE LOGITS
     £
    1.57
     licences
    1.45
     apologised
    1.44
     enqu
    1.43
     licence
    1.42
     apologise
    1.36
     solicitor
    1.34
     offences
    1.33
     councillor
    1.33
     councillors
    1.32
    Activations Density 0.884%

    No Known Activations