© 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. 10-RES-JB
    11. 10743
    Prev
    Next
    INDEX
    Explanations

    phrases related to various forms of collapse or failure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to failures or collapses in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entertained
    -0.85
    omorph
    -0.66
    icons
    -0.63
    ios
    -0.62
    visual
    -0.62
     entert
    -0.61
    orney
    -0.57
    inal
    -0.57
     computed
    -0.57
     reserved
    -0.57
    POSITIVE LOGITS
     prematurely
    1.24
     unexpectedly
    1.22
     mysteriously
    1.19
     abruptly
    1.12
     tragically
    1.08
     miser
    1.07
     catast
    1.03
     horribly
    0.92
     intest
    0.89
     owing
    0.89
    Activations Density 0.191%

    No Known Activations