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. 5-RES-JB
    6. 1061
    Prev
    Next
    INDEX
    Explanations

    references to superlatives, particularly indicating the highest degree or extent of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "one of the" followed by a noun or noun phrase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.81
    ENCE
    -0.71
    leeve
    -0.71
    oney
    -0.70
    SPONSORED
    -0.67
    fulness
    -0.66
    Ly
    -0.66
    LIST
    -0.65
    govtrack
    -0.65
    CLE
    -0.65
    POSITIVE LOGITS
     earliest
    1.00
     largest
    0.90
     busiest
    0.89
     aforementioned
    0.89
     strongest
    0.89
     highest
    0.88
     finest
    0.85
     greatest
    0.84
    ses
    0.83
     hardest
    0.82
    Activations Density 0.127%

    No Known Activations