© 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. 2-RES-JB
    11. 24000
    Prev
    Next
    INDEX
    Explanations

    mentions of musical themes or references in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "music."

    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
     Diet
    -0.67
     Spartan
    -0.66
    than
    -0.65
    teen
    -0.64
     Recon
    -0.63
     Kis
    -0.62
     Duc
    -0.60
     Chiefs
    -0.60
    fty
    -0.60
     Span
    -0.60
    POSITIVE LOGITS
     notation
    1.02
     music
    0.99
     lyrics
    0.98
     playlist
    0.86
     concerts
    0.85
     compositions
    0.85
    stress
    0.83
    isphere
    0.83
     rehearsal
    0.82
    mith
    0.81
    Activations Density 0.022%

    No Known Activations