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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 10676
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific terms or concepts within a context, such as "God" or "America First."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of identity and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glou
    -0.68
     Ambro
    -0.66
     incent
    -0.65
     Skydragon
    -0.65
    Buyable
    -0.62
     Somers
    -0.61
     mathemat
    -0.61
     Silk
    -0.60
     Orange
    -0.60
     Doctors
    -0.60
    POSITIVE LOGITS
    Ļ
    1.18
    ħ
    1.15
    ¬
    1.14
    Ĵ
    1.10
    Ķ
    1.09
    ı
    1.06
    ¤
    1.05
    ¯
    1.02
    ĸ
    1.00
    ĺ
    0.99
    Activations Density 0.206%

    No Known Activations