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. 11036
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to application tracking and management

    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
     Beir
    -0.40
     conclud
    -0.36
     Frie
    -0.33
     rul
    -0.32
     Vaugh
    -0.32
    chnology
    -0.32
    enegger
    -0.31
     moreover
    -0.29
     Adin
    -0.29
    abee
    -0.29
    POSITIVE LOGITS
    wcsstore
    0.32
     dads
    0.31
    natureconservancy
    0.27
     sins
    0.27
     pics
    0.27
    Joined
    0.27
     moms
    0.26
     dudes
    0.26
     pops
    0.25
    bles
    0.24
    Activations Density 4.390%

    No Known Activations