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. 0-RES-JB
    6. 21178
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms, potentially related to news or current events

    oai_token-act-pair · gpt-3.5-turbo

    references to the Nusra Front and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hi
    -0.83
     aisle
    -0.67
     Hi
    -0.66
     Prem
    -0.64
     hangs
    -0.63
     ante
    -0.63
     Cand
    -0.63
     Postal
    -0.62
     Build
    -0.62
     Jew
    -0.61
    POSITIVE LOGITS
    Nusra
    3.56
    usra
    3.44
    ousse
    1.59
     YPG
    1.20
     brutality
    1.05
    qqa
    1.05
    Sham
    0.97
     FSA
    0.96
     Defenders
    0.96
    odon
    0.94
    Activations Density 0.035%

    No Known Activations