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. 11-RES-JB
    6. 18305
    Prev
    Next
    INDEX
    Explanations

    words related to determination, hard work, perseverance, and dedication

    oai_token-act-pair · gpt-3.5-turbo

    words and concepts related to personal and collective strength, resilience, and positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sabha
    -0.76
    ãĥ´
    -0.69
    oval
    -0.67
    kef
    -0.66
    ãĥĺãĥ©
    -0.65
    ophon
    -0.65
    location
    -0.65
    iatus
    -0.64
    pheus
    -0.62
    react
    -0.62
    POSITIVE LOGITS
    fulness
    1.20
     bordering
    1.13
    lessness
    1.07
    worthiness
    1.00
     exhibited
    0.99
     toward
    0.97
     towards
    0.95
     tempered
    0.94
     rewarded
    0.92
     displayed
    0.90
    Activations Density 0.246%

    No Known Activations