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. 20244
    Prev
    Next
    INDEX
    Explanations

    words related to intelligence

    oai_token-act-pair · gpt-3.5-turbo

    references to intelligence in various contexts

    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
    MY
    -0.85
    rine
    -0.77
     Bundy
    -0.77
    Snow
    -0.76
    href
    -0.75
    ANA
    -0.72
    VK
    -0.72
    utz
    -0.68
    cdn
    -0.67
    cial
    -0.66
    POSITIVE LOGITS
    elligent
    1.19
     intelligent
    1.11
     intellig
    1.00
     quot
    0.91
     Intelligent
    0.86
    nesses
    0.86
     beings
    0.83
     enough
    0.80
     minded
    0.79
    ness
    0.77
    Activations Density 0.013%

    No Known Activations