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. 11760
    Prev
    Next
    INDEX
    Explanations

    phrases related to data protection, data sets, and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data protection and privacy

    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
    Rated
    -0.73
    KK
    -0.69
    kins
    -0.69
    mare
    -0.67
    ogun
    -0.67
    dan
    -0.63
    iev
    -0.63
    Minecraft
    -0.62
    Sund
    -0.62
    ç
    -0.60
    POSITIVE LOGITS
    abytes
    1.01
    chnology
    0.77
     parsed
    0.76
     folders
    0.74
     GOODMAN
    0.73
    intensive
    0.72
     databases
    0.72
     backups
    0.71
     analysed
    0.70
    collection
    0.70
    Activations Density 0.529%

    No Known Activations