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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3324
    Prev
    Next
    INDEX
    Explanations

    names related to the term "Jam"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jam" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.82
     Highlander
    -0.76
     Subtle
    -0.72
     particulars
    -0.69
     reserved
    -0.62
     rare
    -0.61
     Scientific
    -0.60
     Clicker
    -0.60
     Nietzsche
    -0.59
     unexplained
    -0.59
    POSITIVE LOGITS
     Jam
    1.19
    Jam
    1.17
    jam
    1.05
    mond
    0.95
    oon
    0.94
    ming
    0.94
    antine
    0.93
    iah
    0.91
    ón
    0.88
    mer
    0.88
    Activations Density 0.004%

    No Known Activations