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. 3140
    Prev
    Next
    INDEX
    Explanations

    references to the word "mobile."

    oai_token-act-pair · gpt-3.5-turbo

    words related to mobile technology and automobiles

    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
     Shard
    -0.74
     Rahman
    -0.69
     MEP
    -0.67
     Stras
    -0.67
     seq
    -0.67
     horm
    -0.65
     Yin
    -0.64
     Horowitz
    -0.63
     Shapiro
    -0.62
     Kats
    -0.62
    POSITIVE LOGITS
    obile
    2.35
    ranch
    1.94
    ountain
    1.80
    ovable
    1.80
    issions
    1.58
    obiles
    1.52
    ission
    1.51
     Sprint
    1.38
    irs
    1.20
     Fountain
    1.18
    Activations Density 0.053%

    No Known Activations