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. 1-RES-JB
    6. 17461
    Prev
    Next
    INDEX
    Explanations

    comparisons or similarities between different concepts

    oai_token-act-pair · gpt-3.5-turbo

    comparisons and analogies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.74
    Published
    -0.72
     Sunshine
    -0.67
    edes
    -0.65
    eds
    -0.63
    tan
    -0.62
     Dresden
    -0.62
     Monaco
    -0.62
     Maple
    -0.61
    Supp
    -0.61
    POSITIVE LOGITS
     akin
    1.22
    lihood
    1.12
    interstitial
    1.10
    etheless
    0.93
    awei
    0.92
    entimes
    0.91
    MpServer
    0.91
    mares
    0.88
    htaking
    0.85
    ĸļ
    0.81
    Activations Density 0.009%

    No Known Activations