© 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. 0-RES-JB
    11. 2318
    Prev
    Next
    INDEX
    Explanations

    mentions of independent ("indie") productions

    oai_token-act-pair · gpt-3.5-turbo

    references to indie culture and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maul
    -0.69
     Height
    -0.69
    Sche
    -0.67
    perature
    -0.67
    bol
    -0.67
     Caption
    -0.67
    rouse
    -0.66
    Monitor
    -0.66
    oÄŁ
    -0.66
     strengthened
    -0.66
    POSITIVE LOGITS
     indie
    3.52
     Indie
    2.83
     genre
    1.26
     DIY
    1.20
     punk
    1.18
    genre
    1.16
     genres
    1.16
     Uncharted
    1.14
     MMO
    1.13
     startups
    1.12
    Activations Density 0.015%

    No Known Activations