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. 10-RES-JB
    6. 19210
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'as' and containing certain words related to chaotic situations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of possessive forms or possessive constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.66
     remed
    -0.65
     synerg
    -0.65
     Mous
    -0.64
     harmon
    -0.64
     handshake
    -0.64
     RIS
    -0.63
     warp
    -0.63
     dispers
    -0.63
     fortun
    -0.61
    POSITIVE LOGITS
    ¬
    1.28
    ı
    1.27
    ¡
    1.25
    Ī
    1.19
    ª
    1.16
    ¹
    1.14
    ķ
    1.13
    ħ
    1.11
    Ĵ
    1.11
    į
    1.10
    Activations Density 0.241%

    No Known Activations