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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17773
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Lloyd's Pharmacy"

    oai_token-act-pair · gpt-3.5-turbo

    the brand name "Lloyds Pharmacy."

    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
    ãĥ¼ãĥĨ
    -0.91
    rawdownloadcloneembedreportprint
    -0.83
    REDACTED
    -0.82
    ãĥį
    -0.82
    姫
    -0.80
     Pastebin
    -0.80
    åij
    -0.78
    ãĥĹ
    -0.76
    æĥ
    -0.76
    tumblr
    -0.74
    POSITIVE LOGITS
     Ll
    1.05
    anca
    1.02
    oyd
    0.99
    asso
    0.98
    ibrary
    0.93
    estial
    0.89
    ength
    0.88
    uci
    0.87
    argo
    0.86
    ava
    0.86
    Activations Density 0.008%

    No Known Activations