© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1243
    Prev
    Next
    INDEX
    Explanations

    words related to titles of media tracks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to music and its elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     practicable
    -0.84
     costly
    -0.77
     printers
    -0.76
     advantageous
    -0.76
     abolished
    -0.74
     veter
    -0.74
    anmar
    -0.73
     manufact
    -0.73
     standardized
    -0.73
     accustomed
    -0.73
    POSITIVE LOGITS
    feat
    1.42
     Remix
    1.42
     vocals
    1.28
     Trance
    1.19
     Album
    1.17
     lyrics
    1.17
     Eminem
    1.16
     remix
    1.15
     Intro
    1.14
    DJ
    1.13
    Activations Density 0.167%

    No Known Activations