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. 4097
    Prev
    Next
    INDEX
    Explanations

    names of people or places ending in "ighton" and possibly other variations of names like "inda" and "otin."

    oai_token-act-pair · gpt-3.5-turbo

    names or references to specific individuals and organizations

    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
    RT
    -0.74
    xes
    -0.74
    KY
    -0.72
    ku
    -0.70
    aic
    -0.68
    CI
    -0.64
    «
    -0.62
    xia
    -0.61
     Abbas
    -0.60
    ACY
    -0.59
    POSITIVE LOGITS
    uyomi
    0.85
    vironment
    0.79
    ication
    0.78
    icated
    0.77
    krit
    0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.75
    matter
    0.72
    scill
    0.71
    eren
    0.70
    iterranean
    0.69
    Activations Density 0.054%

    No Known Activations