© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 21604
    Prev
    Next
    INDEX
    Explanations

    references to transparency and accountability in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to promoting transparency and accountability

    oai_token-act-pair · gpt-3.5-turbo
    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
    Champ
    -0.80
    ãĤ©
    -0.77
    Hero
    -0.74
    esome
    -0.74
    uin
    -0.72
    dad
    -0.70
    stall
    -0.70
    Wi
    -0.67
    assium
    -0.67
    Sold
    -0.66
    POSITIVE LOGITS
     lieu
    1.32
     regards
    1.32
     favor
    1.26
     accordance
    1.26
     favour
    1.22
     relation
    1.19
     pursuit
    1.18
     regard
    1.18
     order
    1.07
    effic
    1.04
    Activations Density 0.218%

    No Known Activations