© 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. 18601
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements to stop something, often in a conflict or legal context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ceasefires and their implications

    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
    hetti
    -0.83
    allo
    -0.72
    imov
    -0.72
    ammy
    -0.70
    ested
    -0.70
    abytes
    -0.67
    abyte
    -0.66
    çīĪ
    -0.64
    Redd
    -0.62
    rics
    -0.61
    POSITIVE LOGITS
     hostilities
    1.08
    fires
    0.97
     disbelief
    0.84
    rences
    0.84
     reliance
    0.78
    soever
    0.77
     emitting
    0.76
     withdrawals
    0.76
    rent
    0.75
    ²¾
    0.75
    Activations Density 0.039%

    No Known Activations