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. 22564
    Prev
    Next
    INDEX
    Explanations

    Japanese names of artists or creators

    oai_token-act-pair · gpt-3.5-turbo

    names of creators and contributors in relation to a specific project or medium

    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
    Colorado
    -0.91
     Colorado
    -0.78
    pes
    -0.70
    cro
    -0.69
    aneers
    -0.69
    vantage
    -0.68
     cocaine
    -0.68
     Pyth
    -0.67
    olitics
    -0.67
     fec
    -0.67
    POSITIVE LOGITS
     Tsuk
    1.33
    ichi
    1.22
     Yosh
    1.21
    ji
    1.14
     Akira
    1.12
     Yamato
    1.09
     Kuro
    1.09
    jin
    1.06
     Shib
    1.06
     Shogun
    1.05
    Activations Density 0.147%

    No Known Activations