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. 18246
    Prev
    Next
    INDEX
    Explanations

    words related to hope and aspirations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and anticipation

    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
    assed
    -0.74
    cedented
    -0.74
    ighed
    -0.74
    assing
    -0.72
    chnology
    -0.72
    è¯
    -0.70
    ascript
    -0.67
    illian
    -0.67
    ifa
    -0.65
    versions
    -0.65
    POSITIVE LOGITS
     someday
    1.07
     to
    1.00
     that
    0.98
     someone
    0.83
     others
    0.79
     they
    0.78
     somebody
    0.77
     whoever
    0.73
     for
    0.73
     nothing
    0.69
    Activations Density 0.061%

    No Known Activations