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. 2-RES-JB
    6. 8570
    Prev
    Next
    INDEX
    Explanations

    mentions of different technology platforms and devices, specifically iOS and Android

    oai_token-act-pair · gpt-3.5-turbo

    references to mobile platforms and their compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WARN
    -0.51
    76561
    -0.46
    minist
    -0.46
    channelAvailability
    -0.45
    natureconservancy
    -0.44
    terness
    -0.43
    pmwiki
    -0.43
     cull
    -0.41
    awar
    -0.41
    nces
    -0.41
    POSITIVE LOGITS
     equivalents
    0.53
    /$
    0.44
     Indies
    0.40
     counterparts
    0.39
    *.
    0.39
    ب
    0.38
    ت
    0.38
    ãģ¾
    0.37
    ãĢģ
    0.37
    Ruby
    0.37
    Activations Density 2.654%

    No Known Activations