© 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. 11-RES-JB
    11. 20350
    Prev
    Next
    INDEX
    Explanations

    mentions of visual arts, animation techniques, and movie-making processes

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic practices and techniques

    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
    isSpecialOrderable
    -0.88
    iatus
    -0.84
     Costco
    -0.82
    chel
    -0.80
    Registration
    -0.76
    leaders
    -0.76
    Wallet
    -0.75
    Answer
    -0.75
    fleet
    -0.74
    ticket
    -0.73
    POSITIVE LOGITS
     compos
    1.42
     animation
    1.30
     filmmaking
    1.29
     painter
    1.26
     cinem
    1.23
     surreal
    1.21
     compositions
    1.19
     synthes
    1.18
     synthesis
    1.15
     cinematic
    1.14
    Activations Density 0.671%

    No Known Activations