© 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. 13463
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to music or entities that have the word "rock" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to the music genre "rock."

    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
    ntil
    -0.78
     Lauder
    -0.66
     circ
    -0.65
     NOTICE
    -0.64
     Cla
    -0.63
     temporal
    -0.60
     Hurricanes
    -0.60
     distracted
    -0.59
     vit
    -0.59
     Verd
    -0.58
    POSITIVE LOGITS
    rock
    1.23
    lake
    0.95
    fall
    0.92
    stead
    0.87
    Rock
    0.86
    strap
    0.86
    eting
    0.85
    beat
    0.83
    Connector
    0.83
    tree
    0.82
    Activations Density 0.005%

    No Known Activations