© 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. 19254
    Prev
    Next
    INDEX
    Explanations

    references to entertainment companies or industry-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to various entertainment companies or 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
    regn
    -0.72
    cycl
    -0.70
    pins
    -0.66
     recip
    -0.66
     bapt
    -0.65
     peg
    -0.64
     traced
    -0.64
     trace
    -0.64
     regress
    -0.64
     gaps
    -0.62
    POSITIVE LOGITS
     Entertainment
    3.87
    tainment
    1.97
     entertainment
    1.87
     Gaming
    1.59
     Productions
    1.52
     Studios
    1.46
     Films
    1.42
     Comics
    1.41
    Gaming
    1.39
     Games
    1.37
    Activations Density 0.010%

    No Known Activations