© 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. 10-RES-JB
    11. 10282
    Prev
    Next
    INDEX
    Explanations

    music artists and band names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific musicians, bands, and their works

    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
    ORPG
    -0.76
     privacy
    -0.71
    iasis
    -0.71
    Ħ¢
    -0.68
     spoiler
    -0.67
     goodwill
    -0.67
     liability
    -0.67
     impartial
    -0.66
     captcha
    -0.65
     unarmed
    -0.65
    POSITIVE LOGITS
     vocals
    1.26
     Guitar
    1.21
     drummer
    1.16
     Orchestra
    1.14
     Rhythm
    1.13
     Funk
    1.10
     guitarist
    1.10
    Music
    1.10
     Remix
    1.09
     Music
    1.08
    Activations Density 0.296%

    No Known Activations