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. 4-RES-JB
    6. 12646
    Prev
    Next
    INDEX
    Explanations

    words related to household appliances

    oai_token-act-pair · gpt-3.5-turbo

    references to appliances and their functionalities

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

    No Comments

    Negative Logits
    imeter
    -0.93
    yll
    -0.85
    ffiti
    -0.82
    uable
    -0.81
    isers
    -0.81
    utterstock
    -0.78
    icial
    -0.78
    opher
    -0.77
    orns
    -0.77
    adows
    -0.76
    POSITIVE LOGITS
    dayName
    0.75
     glut
    0.72
    MpServer
    0.69
    Accessory
    0.67
    dylib
    0.67
     GOT
    0.66
     welf
    0.65
    20439
    0.65
     CN
    0.63
    cffffcc
    0.62
    Activations Density 0.041%

    No Known Activations