© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 4953
    Prev
    Next
    INDEX
    Explanations

    phrases related to action and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to nature and environmental concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brist
    -0.89
     Wichita
    -0.88
     maple
    -0.81
     fossil
    -0.80
     contingency
    -0.80
     crocod
    -0.79
     Foss
    -0.76
     mathemat
    -0.75
     Tup
    -0.75
     pipeline
    -0.74
    POSITIVE LOGITS
    Ļ
    1.70
    à¨
    1.24
    âĹı
    1.23
    ç¥ŀ
    1.20
    ãĤ¬
    1.19
    Ã
    1.16
    ãĥ©ãĥ³
    1.13
     à¨
    1.13
    Gil
    1.11
    É
    1.11
    Activations Density 0.177%

    No Known Activations