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. 8216
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking terms

    oai_token-act-pair · gpt-3.5-turbo

    various forms of food and drink items, as well as measurements and quantities related to them

    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
    ãĤ¨ãĥ«
    -0.82
    ccording
    -0.69
    anmar
    -0.64
    ioxide
    -0.59
    æ©
    -0.59
    ©¶æ¥µ
    -0.59
    ģĸ
    -0.58
    ãĤ¶
    -0.57
    ãĤ¢ãĥ«
    -0.57
    ISA
    -0.57
    POSITIVE LOGITS
    gets
    0.54
     sessions
    0.52
     motivational
    0.52
     etc
    0.52
    achine
    0.51
     CLSID
    0.51
    bane
    0.50
    âĢij
    0.50
     scrolls
    0.49
     nails
    0.48
    Activations Density 1.583%

    No Known Activations