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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20830
    Prev
    Next
    INDEX
    Explanations

    words related to internet and internet services

    oai_token-act-pair · gpt-3.5-turbo
    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
    lein
    -0.81
    geries
    -0.76
    ilts
    -0.75
    nil
    -0.74
    otte
    -0.72
    itzer
    -0.71
     Pearce
    -0.70
    lie
    -0.67
    roth
    -0.67
    士
    -0.66
    POSITIVE LOGITS
     connectivity
    1.06
     cafes
    1.05
     Explorer
    1.02
     cafe
    0.92
     café
    0.91
     connection
    0.90
     caf
    0.87
     gateway
    0.83
     Archive
    0.83
     sockets
    0.82
    Activations Density 0.027%

    No Known Activations