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. 2-RES-JB
    6. 2273
    Prev
    Next
    INDEX
    Explanations

    words related to bridging or connecting different entities, such as people, information, or disciplines

    oai_token-act-pair · gpt-3.5-turbo

    words associated with bridging gaps and linking concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.86
     guiActiveUnfocused
    -0.74
    arial
    -0.73
    ographic
    -0.72
     breath
    -0.68
    IFIED
    -0.63
     VIDEOS
    -0.61
    omon
    -0.61
     Collective
    -0.61
    istar
    -0.59
    POSITIVE LOGITS
    ¸
    1.22
    lling
    1.20
    ´
    1.10
    ·
    1.09
    ¶æ
    1.09
    ling
    1.08
    ller
    1.05
    llers
    1.04
    ¶
    1.01
    ¹
    1.01
    Activations Density 0.029%

    No Known Activations