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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 14634
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "say," is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "say," indicating a focus on quoted dialogue or statements

    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
    SD
    -0.78
    OGR
    -0.78
    ason
    -0.74
    SF
    -0.71
    HO
    -0.71
    Valid
    -0.68
    URE
    -0.65
    ife
    -0.64
    olesterol
    -0.64
    ures
    -0.64
    POSITIVE LOGITS
     boycott
    0.64
     grap
    0.62
     boycot
    0.62
    krit
    0.60
     revenge
    0.60
     Dog
    0.60
    nikov
    0.59
     retribution
    0.59
     proto
    0.59
     Amos
    0.59
    Activations Density 0.065%

    No Known Activations