© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20454
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating coincidence or circumstance

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the structure "happened to be."

    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
    ãĤ¦ãĤ¹
    -0.78
    intensive
    -0.69
    Log
    -0.67
    urized
    -0.67
     Limits
    -0.66
    chlor
    -0.66
    rar
    -0.65
    lime
    -0.65
    Easy
    -0.65
    simple
    -0.64
    POSITIVE LOGITS
     coincide
    1.21
     stumble
    1.19
     reside
    1.00
     befriend
    0.94
     belong
    0.91
     resemble
    0.89
     meet
    0.88
     be
    0.86
     stumbled
    0.85
     inherit
    0.84
    Activations Density 0.101%

    No Known Activations