© 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. 16101
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative impacts or severe consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote significant negative impacts or setbacks

    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
     livest
    -0.81
    cius
    -0.62
    nesota
    -0.61
     branches
    -0.61
     Halls
    -0.61
     calendars
    -0.60
     ancestors
    -0.59
     channels
    -0.58
     Empires
    -0.58
    cients
    -0.57
    POSITIVE LOGITS
    hearted
    0.97
    blow
    0.94
    hard
    0.92
    warming
    0.89
     against
    0.86
    pun
    0.86
     inflicted
    0.83
    ingly
    0.81
    wart
    0.81
    warm
    0.80
    Activations Density 0.076%

    No Known Activations