© 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. 0-RES-JB
    11. 8387
    Prev
    Next
    INDEX
    Explanations

    instances of musical instruments, particularly the piano

    oai_token-act-pair · gpt-3.5-turbo

    references to the piano

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneers
    -0.86
    Gre
    -0.77
    GW
    -0.75
    network
    -0.74
     Rand
    -0.74
     NETWORK
    -0.73
    Cow
    -0.73
     Holdings
    -0.72
    ablishment
    -0.72
    Tokens
    -0.72
    POSITIVE LOGITS
     piano
    3.12
     Piano
    2.46
     pian
    2.37
     violin
    2.34
     sax
    1.84
     drums
    1.83
     viol
    1.77
     guitar
    1.66
     percussion
    1.56
     vocals
    1.56
    Activations Density 0.046%

    No Known Activations