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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 6022
    Prev
    Next
    INDEX
    Explanations

    words related to international names and surnames

    oai_token-act-pair · gpt-3.5-turbo

    words or names that start with the letter "K."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mantle
    -0.62
    Versions
    -0.60
    redients
    -0.58
    ensional
    -0.57
     Gabriel
    -0.56
     mund
    -0.56
    ancial
    -0.55
     Paddock
    -0.55
    å°Ĩ
    -0.55
     Huss
    -0.54
    POSITIVE LOGITS
    ikuman
    1.18
     Lumpur
    1.05
    enei
    1.02
    lyak
    1.02
    zie
    0.94
    EStreamFrame
    0.91
    aroo
    0.82
    aston
    0.81
    waukee
    0.81
    chuk
    0.79
    Activations Density 0.092%

    No Known Activations