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. 8-RES-JB
    6. 17882
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences beginning with the word "Simply"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "simply" and its variations, indicating simplification or straightforward expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egal
    -0.72
    amia
    -0.68
    undai
    -0.66
     enthus
    -0.65
     developments
    -0.62
     extensively
    -0.62
    afort
    -0.61
    alez
    -0.60
    emis
    -0.60
    ajo
    -0.59
    POSITIVE LOGITS
    IFIED
    0.80
     shrugged
    0.74
     untrue
    0.72
    ãģį
    0.71
    ifiable
    0.69
     stated
    0.68
    ified
    0.68
     redistributed
    0.67
    ãĥ´
    0.67
    clair
    0.64
    Activations Density 0.046%

    No Known Activations