© 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. 1818
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or characters with the last name "upp" and possibly variations

    oai_token-act-pair · gpt-3.5-turbo

    references to puppet-related terms and characters

    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
    76561
    -0.78
    ãĥīãĥ©ãĤ´ãĥ³
    -0.76
     willful
    -0.69
     penetrating
    -0.69
     faint
    -0.67
    å°Ĩ
    -0.66
     Binding
    -0.66
    LESS
    -0.66
     blot
    -0.65
     dissolution
    -0.65
    POSITIVE LOGITS
    ortun
    1.15
    sburgh
    1.09
    olicy
    1.08
    enhagen
    1.08
    enthal
    1.02
    esy
    0.98
    upp
    0.95
    ete
    0.94
    onent
    0.94
    etry
    0.93
    Activations Density 0.005%

    No Known Activations