Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 8104
    Prev
    Next
    INDEX
    Explanations

    terms related to challenging or tumultuous situations

    oai_token-act-pair · gpt-3.5-turbo
    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
    ifles
    -0.87
    ernels
    -0.77
    osponsors
    -0.75
    pires
    -0.74
    pees
    -0.70
    kus
    -0.70
    icts
    -0.70
    Requires
    -0.69
    Ingredients
    -0.69
    interstitial
    -0.67
    POSITIVE LOGITS
     week
    1.18
     weekend
    1.10
     fortnight
    1.07
     month
    1.06
     offseason
    1.02
     summer
    1.00
     period
    1.00
     day
    0.98
     year
    0.98
     journey
    0.96
    Activations Density 0.143%

    No Known Activations