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. 2532
    Prev
    Next
    INDEX
    Explanations

    terms related to religious activities, specifically those associated with the observance of the Sabbath

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands or types of appliances, particularly those related to cooking

    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
    catentry
    -0.80
    è¦ļéĨĴ
    -0.74
     lacking
    -0.69
    ALLY
    -0.66
     unaccompanied
    -0.63
     Kinnikuman
    -0.61
     Berm
    -0.61
     dement
    -0.60
    GGGGGGGG
    -0.60
    DragonMagazine
    -0.58
    POSITIVE LOGITS
    inki
    0.97
    ghai
    0.96
    tty
    0.90
    bole
    0.89
    idan
    0.85
    puff
    0.83
    ĸļ
    0.82
    schild
    0.80
    nit
    0.79
    ulu
    0.78
    Activations Density 0.099%

    No Known Activations