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. 3-RES-JB
    6. 19754
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     royalty
    -0.70
     sparing
    -0.68
     royalties
    -0.68
     domestic
    -0.64
     bribery
    -0.64
     translator
    -0.63
     KEY
    -0.62
     paying
    -0.61
     paed
    -0.61
     shampoo
    -0.61
    POSITIVE LOGITS
    uti
    0.84
    ulkan
    0.83
    lucent
    0.80
    utions
    0.78
    ounces
    0.76
    eteria
    0.76
    icip
    0.75
    ages
    0.73
    estern
    0.73
    ongs
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.