© 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. 20661
    Prev
    Next
    INDEX
    Explanations

    references to technology companies and services

    oai_token-act-pair · gpt-3.5-turbo

    references to popular internet platforms and their functionalities

    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
    ufact
    -0.69
    iscal
    -0.69
    cised
    -0.68
    enary
    -0.68
    HAEL
    -0.67
     wastes
    -0.65
    bishop
    -0.65
     blinding
    -0.65
    baugh
    -0.64
    genic
    -0.64
    POSITIVE LOGITS
     Pinterest
    1.59
     Yelp
    1.50
     Dropbox
    1.49
     LinkedIn
    1.44
     Tumblr
    1.44
     Gmail
    1.42
     Snapchat
    1.42
     Spotify
    1.40
     Airbnb
    1.40
     Instagram
    1.39
    Activations Density 0.180%

    No Known Activations