Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 13921
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues or legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific author or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.77
     convol
    -0.66
    reverse
    -0.62
     equ
    -0.62
     ranked
    -0.62
     liaison
    -0.60
     eternal
    -0.59
    laws
    -0.59
    æĪ¦
    -0.59
    conservancy
    -0.58
    POSITIVE LOGITS
    het
    1.28
    icals
    1.15
    amines
    1.12
    rette
    1.09
    ype
    1.07
    oric
    1.01
    nikov
    0.98
    ypes
    0.98
    orically
    0.97
    eless
    0.97
    Activations Density 0.009%

    No Known Activations