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. 20570
    Prev
    Next
    INDEX
    Explanations

    difficult and challenging situations or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concepts of difficulty and ease

    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
    krit
    -0.73
    ateurs
    -0.72
    gross
    -0.72
    ften
    -0.71
    aware
    -0.70
    uber
    -0.69
    uality
    -0.68
    icip
    -0.67
    ubi
    -0.67
    uine
    -0.65
    POSITIVE LOGITS
     adolesc
    0.98
     situation
    0.95
     task
    0.91
     circumstances
    0.88
     situations
    0.87
     predicament
    0.85
     journey
    0.82
     terrain
    0.81
     road
    0.80
     breakup
    0.80
    Activations Density 0.093%

    No Known Activations