© 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. 3-RES-JB
    6. 12986
    Prev
    Next
    INDEX
    Explanations

    phrases related to music and musicians, possibly focusing on specific names or genres

    oai_token-act-pair · gpt-3.5-turbo

    musical references or terminologies within the context of music discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comprom
    -0.75
     Lockheed
    -0.71
     Chocobo
    -0.69
    EStreamFrame
    -0.69
     Lenovo
    -0.69
     Gorsuch
    -0.66
     UID
    -0.66
    osate
    -0.66
    Senate
    -0.65
    ewitness
    -0.65
    POSITIVE LOGITS
     albums
    1.25
     lyrics
    1.20
     songs
    1.14
     rappers
    1.14
     vocals
    1.12
     album
    1.12
     Songs
    1.09
     music
    1.07
     tunes
    1.07
    music
    1.04
    Activations Density 0.799%

    No Known Activations