© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 17147
    Prev
    Next
    INDEX
    Explanations

    information relating to local products, services, or businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to locally sourced food and ingredients

    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
    Reply
    -0.63
     Mandatory
    -0.60
    iatus
    -0.56
    uddin
    -0.54
    DOC
    -0.53
    ggle
    -0.51
    Latest
    -0.51
    edge
    -0.50
    cess
    -0.50
    {{
    -0.50
    POSITIVE LOGITS
     notwithstanding
    0.74
     preferably
    0.64
    thirds
    0.64
     heirs
    0.60
     economists
    0.60
     nonetheless
    0.58
    ãĥĺ
    0.57
     skipping
    0.55
    =]
    0.55
    netflix
    0.55
    Activations Density 4.477%

    No Known Activations