© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 5766
    Prev
    Next
    INDEX
    Explanations

    phrases related to albums, releases, and music

    oai_token-act-pair · gpt-3.5-turbo

    references to musical albums and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Wikipedia
    -0.76
    SQL
    -0.74
    poke
    -0.73
     Wikimedia
    -0.73
     rigging
    -0.73
    CTV
    -0.72
    Actor
    -0.72
     actu
    -0.70
    Mayor
    -0.70
     betting
    -0.70
    POSITIVE LOGITS
     album
    1.44
     Album
    1.25
     albums
    1.24
    itled
    1.17
    album
    1.15
     Songs
    1.14
    released
    1.11
     singles
    1.09
     EP
    1.08
     Remix
    1.08
    Activations Density 0.301%

    No Known Activations