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. 3-RES-JB
    6. 22372
    Prev
    Next
    INDEX
    Explanations

    mentions of the retail store "Target."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Target."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geological
    -0.73
     Oliv
    -0.72
     traged
    -0.70
    UGE
    -0.62
    aut
    -0.62
    galitarian
    -0.60
    URR
    -0.60
     oxide
    -0.59
     unlikely
    -0.59
     equ
    -0.58
    POSITIVE LOGITS
    ted
    0.86
    Target
    0.82
    achusetts
    0.79
     Target
    0.79
    izen
    0.75
     Pilgrim
    0.75
    stadt
    0.73
    edin
    0.73
    pling
    0.72
    ileaks
    0.72
    Activations Density 0.011%

    No Known Activations