© 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. 1-RES-JB
    11. 11142
    Prev
    Next
    INDEX
    Explanations

    the word "vien" in different contexts which is likely a specific and important term in the trained data

    oai_token-act-pair · gpt-3.5-turbo

    words related to scientific or technological terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.92
    ramid
    -0.76
     mids
    -0.71
    Discussion
    -0.69
     recess
    -0.67
    rooms
    -0.65
    tub
    -0.64
     variance
    -0.62
    mable
    -0.62
     EVs
    -0.62
    POSITIVE LOGITS
    ien
    1.19
    emy
    1.05
    cia
    0.96
    icidal
    0.91
    vironment
    0.90
    emort
    0.88
    lein
    0.87
    eman
    0.85
    eme
    0.84
    clair
    0.84
    Activations Density 0.005%

    No Known Activations