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. 18168
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a position of being behind or falling behind in a competition or comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "behind" in varying contexts

    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
    oret
    -0.75
     Pwr
    -0.73
    enegger
    -0.70
    isms
    -0.65
     vic
    -0.64
    eri
    -0.64
    owe
    -0.64
    elf
    -0.64
    istic
    -0.64
    escal
    -0.62
    POSITIVE LOGITS
    ienced
    0.81
    shore
    0.76
     schedule
    0.70
    âĸ¬âĸ¬
    0.69
    coat
    0.66
    beat
    0.66
     bars
    0.64
    stood
    0.64
    oos
    0.62
    roups
    0.61
    Activations Density 0.016%

    No Known Activations