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. 8-RES-JB
    6. 4714
    Prev
    Next
    INDEX
    Explanations

    terms related to data analytics and predictive analytics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data analytics and its applications

    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
     Rez
    -0.81
    enegger
    -0.79
    ength
    -0.78
    lain
    -0.76
    boats
    -0.73
    hood
    -0.73
    cakes
    -0.73
    bered
    -0.71
    ington
    -0.71
    adder
    -0.71
    POSITIVE LOGITS
     analytics
    1.26
     Analytics
    1.03
    analy
    0.92
     methodology
    0.88
     dashboard
    0.87
    tics
    0.85
     metrics
    0.83
    urus
    0.82
     analytic
    0.82
     compute
    0.80
    Activations Density 0.091%

    No Known Activations