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. 7904
    Prev
    Next
    INDEX
    Explanations

    words related to supersonic characteristics or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to submarines

    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
    hyde
    -0.83
     Weir
    -0.64
     AE
    -0.64
     Remastered
    -0.63
     Orbit
    -0.63
    naires
    -0.62
     Painter
    -0.62
     Lyme
    -0.62
    wright
    -0.61
     Ashton
    -0.61
    POSITIVE LOGITS
    cess
    1.09
    ccess
    1.07
    arez
    1.06
    zanne
    1.05
    nder
    1.05
    ction
    1.05
    perm
    1.04
    prisingly
    1.02
    ceed
    1.00
    pert
    1.00
    Activations Density 0.012%

    No Known Activations