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. 9533
    Prev
    Next
    INDEX
    Explanations

    names of places such as countries, states, and cities

    oai_token-act-pair · gpt-3.5-turbo

    names of people, countries, and organizations, as well as certain objects and entities

    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
    witz
    -0.77
     VG
    -0.54
     WARN
    -0.54
     mah
    -0.54
     bip
    -0.54
    iman
    -0.53
     Andersen
    -0.53
    lopp
    -0.53
     presumptive
    -0.53
    ebus
    -0.53
    POSITIVE LOGITS
     respectively
    1.01
    SPONSORED
    0.76
    â̦.
    0.73
     alike
    0.68
    *.
    0.68
    ;
    0.67
    â̦
    0.67
     etc
    0.66
     among
    0.65
     amongst
    0.64
    Activations Density 0.599%

    No Known Activations