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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 13227
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'double' with a significant emphasis on a subset that appears to be related to contrasting duality

    oai_token-act-pair · gpt-3.5-turbo

    the term "double" used in various contexts, particularly as a prefix in phrases or labels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utical
    -0.85
    ULE
    -0.83
    ALE
    -0.80
    ihara
    -0.76
    utics
    -0.75
    ĸļ
    -0.74
    ä½ľ
    -0.74
    atche
    -0.73
    Interstitial
    -0.72
    istry
    -0.72
    POSITIVE LOGITS
    header
    0.99
     digit
    0.96
     digits
    0.96
     sided
    0.89
    headers
    0.88
     dipping
    0.87
    plet
    0.77
    leaf
    0.76
    handedly
    0.76
    headed
    0.75
    Activations Density 0.026%

    No Known Activations