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. 13033
    Prev
    Next
    INDEX
    Explanations

    locations or specific place names that include the word "Mon" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Mon" followed by various suffixes or additions

    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
     Norn
    -0.89
    OHN
    -0.87
    éĹĺ
    -0.80
    æĸ¹
    -0.78
    ONSORED
    -0.75
    EXP
    -0.74
    ACTED
    -0.74
    ATING
    -0.74
     Pathfinder
    -0.73
    enegger
    -0.72
    POSITIVE LOGITS
    itored
    1.19
    olith
    1.10
    olithic
    1.09
    opoly
    1.03
    stros
    1.02
    astery
    1.02
    roe
    0.97
    ique
    0.94
    ero
    0.91
    soon
    0.90
    Activations Density 0.014%

    No Known Activations