© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    descriptions related to entertainment industry productions and styles

    oai_token-act-pair · gpt-3.5-turbo

    negative connotations or themes associated with specific references or comparisons

    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
     Collins
    -0.68
     square
    -0.68
     negotiator
    -0.67
     Cah
    -0.67
     oral
    -0.67
     intervals
    -0.66
     exha
    -0.65
     Na
    -0.65
     Gallup
    -0.65
     LOT
    -0.65
    POSITIVE LOGITS
    esque
    1.99
    style
    1.96
    themed
    1.93
    inspired
    1.90
    like
    1.73
    type
    1.69
    sized
    1.66
    era
    1.65
    inducing
    1.64
    exclusive
    1.62
    Activations Density 0.103%

    No Known Activations