Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 10682
    Prev
    Next
    INDEX
    Explanations

    musical instruments

    oai_token-act-pair · gpt-3.5-turbo

    musical instruments and terms related to music composition

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

    No Comments

    Negative Logits
     trusted
    -0.71
     Governments
    -0.70
     trustworthy
    -0.68
     autonomous
    -0.66
     warehouses
    -0.65
     governments
    -0.64
    ait
    -0.63
     detain
    -0.62
     Ples
    -0.62
     whichever
    -0.61
    POSITIVE LOGITS
     sax
    0.93
    grass
    0.84
     volleyball
    0.81
    BALL
    0.81
     violin
    0.80
    iculture
    0.79
     slam
    0.77
     chorus
    0.75
     guitar
    0.74
    flat
    0.74
    Activations Density 0.323%

    No Known Activations