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. 10856
    Prev
    Next
    INDEX
    Explanations

    terms related to speed or rapid growth

    oai_token-act-pair · gpt-3.5-turbo

    references to "fast" in relation to food 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
    pheus
    -0.83
     Seym
    -0.80
    cules
    -0.79
    eryl
    -0.79
    ignty
    -0.77
    代
    -0.76
    arks
    -0.75
    vironment
    -0.72
    iverpool
    -0.72
     Contributions
    -0.70
    POSITIVE LOGITS
    idious
    1.40
     paced
    1.25
    ened
    1.10
    eners
    1.07
    ener
    0.93
     asleep
    0.93
    ening
    0.91
    cgi
    0.88
     lear
    0.88
     enough
    0.88
    Activations Density 0.020%

    No Known Activations