© 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. 2428
    Prev
    Next
    INDEX
    Explanations

    information related to movies, TV series, and actors

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks indicating the end of sentences

    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
     mathemat
    -1.07
     mosqu
    -1.00
     municip
    -0.94
     transact
    -0.93
     tremend
    -0.93
    yip
    -0.89
     volunte
    -0.89
     territ
    -0.87
     carbohyd
    -0.87
     citiz
    -0.86
    POSITIVE LOGITS
     Fans
    1.57
     Featuring
    1.42
     Whedon
    1.37
     Producer
    1.32
     Paramount
    1.30
     Variety
    1.29
     Thankfully
    1.27
     Produ
    1.25
     EW
    1.25
     Released
    1.24
    Activations Density 0.333%

    No Known Activations