© 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. 23187
    Prev
    Next
    INDEX
    Explanations

    words related to cinematography and movie theaters

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with cinema and filmmaking

    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
     hands
    -0.68
     Sr
    -0.64
     Belt
    -0.64
     hand
    -0.62
     whichever
    -0.61
     tongue
    -0.61
     lifelong
    -0.60
     fielding
    -0.60
     cover
    -0.59
     prevailing
    -0.59
    POSITIVE LOGITS
    atography
    1.97
    atics
    1.78
    atically
    1.73
    atic
    1.72
    atical
    1.51
    atis
    1.44
    at
    1.38
    agraph
    1.37
    agic
    1.36
    atem
    1.35
    Activations Density 0.064%

    No Known Activations