© 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. 2-RES-JB
    11. 17549
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "unhinged"

    oai_token-act-pair · gpt-3.5-turbo

    words related to "unhinged" or the concept of being "off-balance" or unstable

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.73
    classified
    -0.72
     servicing
    -0.61
     implying
    -0.57
     Sierra
    -0.56
    ×Ļ
    -0.56
    coni
    -0.56
     Heb
    -0.55
     compare
    -0.55
     Mub
    -0.54
    POSITIVE LOGITS
    tons
    1.16
    hing
    0.90
    leys
    0.86
    rish
    0.86
    apeake
    0.83
    redients
    0.81
    edom
    0.80
    ham
    0.79
    ton
    0.79
    eki
    0.79
    Activations Density 0.004%

    No Known Activations