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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 1097
    Prev
    Next
    INDEX
    Explanations

    words related to chemical reactions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "react" in various 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
    holders
    -0.90
    holder
    -0.77
    holding
    -0.70
    abwe
    -0.61
     Maurit
    -0.59
    luster
    -0.59
    ppo
    -0.58
     Panasonic
    -0.58
     Starr
    -0.57
     Mandela
    -0.55
    POSITIVE LOGITS
    ivated
    1.01
    itect
    0.99
    ivation
    0.96
    ivity
    0.93
    ivating
    0.93
    ency
    0.87
    ivities
    0.85
    ors
    0.81
    anooga
    0.81
    angel
    0.80
    Activations Density 0.017%

    No Known Activations