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. 3493
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming languages and projects

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of programs

    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
    Downloadha
    -0.68
     eyeb
    -0.63
     oxide
    -0.61
     incarcer
    -0.61
    ouched
    -0.60
     lash
    -0.60
    ength
    -0.59
     eyel
    -0.59
     deposition
    -0.58
     vig
    -0.58
    POSITIVE LOGITS
    mers
    1.55
    ming
    1.46
    med
    1.37
    mable
    1.29
    mer
    1.26
    mits
    1.06
    mes
    1.05
    ters
    1.05
    mit
    1.03
    metry
    1.02
    Activations Density 0.031%

    No Known Activations