© 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. 23228
    Prev
    Next
    INDEX
    Explanations

    phrases related to being out of place or outdated

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express being out of sync or disconnect from a situation

    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
    MpServer
    -0.82
    _-
    -0.80
    enium
    -0.79
    phal
    -0.76
    é¾įåĸļ士
    -0.74
    cause
    -0.73
    urd
    -0.71
    ulia
    -0.71
    sburg
    -0.68
    vic
    -0.68
    POSITIVE LOGITS
     sync
    1.17
     bounds
    1.12
     touch
    1.01
     tune
    1.01
     place
    0.99
     alignment
    0.95
     fashion
    0.94
     step
    0.94
     date
    0.92
     proportion
    0.88
    Activations Density 0.038%

    No Known Activations