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. 2409
    Prev
    Next
    INDEX
    Explanations

    mixing or combining actions or ingredients in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    references to mixtures or combinations of ingredients in a recipe or process

    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
    ĻĤ
    -0.98
    orth
    -0.74
    £
    -0.70
    blems
    -0.66
    ighth
    -0.65
     Passage
    -0.65
     Borders
    -0.65
    ©¶æ
    -0.65
     Defenders
    -0.63
    shire
    -0.62
    POSITIVE LOGITS
     mixture
    1.02
     blends
    0.91
     conco
    0.88
     mixes
    0.86
     thereof
    0.84
     mix
    0.82
     blend
    0.80
     Flavoring
    0.79
    assium
    0.78
    itionally
    0.76
    Activations Density 0.022%

    No Known Activations