© 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. 2-RES-JB
    11. 17080
    Prev
    Next
    INDEX
    Explanations

    terms related to the name "Jarvis."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or entities, particularly "Jar" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.76
    imity
    -0.72
    Premium
    -0.70
    ancial
    -0.69
     Samoa
    -0.68
    EPA
    -0.67
    buquerque
    -0.67
    phis
    -0.66
    eem
    -0.66
    Interstitial
    -0.65
    POSITIVE LOGITS
    Jar
    1.40
     Jar
    1.30
     jar
    0.99
     jars
    0.96
    ón
    0.95
    assic
    0.86
    van
    0.85
    jar
    0.85
    rod
    0.83
    abul
    0.80
    Activations Density 0.004%

    No Known Activations