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. 10-RES-JB
    6. 10899
    Prev
    Next
    INDEX
    Explanations

    names of science centers, museums, research institutes, and other educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    institution names and their corresponding types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    depending
    -0.77
     destro
    -0.76
    ecause
    -0.71
     tyr
    -0.71
     slic
    -0.70
     tremend
    -0.68
    whatever
    -0.68
     slump
    -0.68
     surpr
    -0.67
    romancer
    -0.67
    POSITIVE LOGITS
     Ltd
    1.20
     LLC
    1.10
     Inc
    1.03
     Limited
    0.99
     Retrieved
    0.98
     LTD
    0.98
     âĵĺ
    0.98
     Collection
    0.98
     Archives
    0.97
     Annual
    0.97
    Activations Density 0.189%

    No Known Activations