© 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. 3-RES-JB
    11. 603
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to the "Kilner" brand or company

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Kilner" brand or the term "Kilner" associated with jars and company names

    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
    ACTED
    -0.80
     Reloaded
    -0.77
    è¯
    -0.77
    ÙIJ
    -0.76
    éļ
    -0.75
    ãģį
    -0.74
    éĹĺ
    -0.74
    ãģ®éŃĶ
    -0.71
     systematic
    -0.71
    æĥ
    -0.70
    POSITIVE LOGITS
    patrick
    1.20
    iman
    0.99
    ometers
    0.96
    oby
    0.96
    nown
    0.95
    roy
    0.95
    kil
    0.93
    oton
    0.88
    mill
    0.87
    gall
    0.87
    Activations Density 0.003%

    No Known Activations