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. 2-RES-JB
    6. 4965
    Prev
    Next
    INDEX
    Explanations

    acronyms related to financial regulatory organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or entity, denoted by the abbreviation "CF"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selves
    -0.72
    Magikarp
    -0.71
    ãĤ°
    -0.70
    felt
    -0.68
    Else
    -0.67
     Klingon
    -0.66
    é¾į
    -0.64
     Tsarnaev
    -0.64
    à
    -0.64
    furt
    -0.63
    POSITIVE LOGITS
    incinn
    0.91
    avorite
    0.91
    ritical
    0.88
    entanyl
    0.85
    enhagen
    0.79
    erate
    0.77
    FW
    0.76
    rosis
    0.76
    yre
    0.76
    amily
    0.75
    Activations Density 0.003%

    No Known Activations