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. 18055
    Prev
    Next
    INDEX
    Explanations

    phrases related to something being out or finished

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "out" and variations of being "off."

    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
    Previous
    -0.74
    gemony
    -0.72
     Presents
    -0.67
    odies
    -0.65
     avoids
    -0.63
    anship
    -0.63
     transitions
    -0.63
    SHIP
    -0.63
     VIDEOS
    -0.62
     relates
    -0.62
    POSITIVE LOGITS
    fitted
    0.83
    rated
    0.75
    enced
    0.72
    going
    0.72
    omorphic
    0.71
    matched
    0.70
    gged
    0.70
    achable
    0.68
    proof
    0.67
    raged
    0.67
    Activations Density 0.197%

    No Known Activations