Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 8711
    Prev
    Next
    INDEX
    Explanations

    instances of the word "oi"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the specific phrase "oi"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sher
    -0.64
     Def
    -0.64
     today
    -0.64
     ignition
    -0.61
     depress
    -0.60
     mine
    -0.60
     shutdown
    -0.59
     patches
    -0.58
     methamphetamine
    -0.58
     slowing
    -0.57
    POSITIVE LOGITS
    oi
    4.90
    ei
    1.42
    oa
    1.34
    ois
    1.28
    oy
    1.13
    oji
    1.10
    OY
    1.07
    oin
    1.04
    oan
    1.03
    arte
    1.03
    Activations Density 0.020%

    No Known Activations