INDEX

Explanations

references to medical degrees, particularly "MD"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.90

AccessFile

-0.79

Izvori

-0.74

BufferException

-0.67

 Luch

-0.65

awtextra

-0.64

 Obre

-0.64

 trypto

-0.62

 otomatig

-0.62

 Mucha

-0.62

POSITIVE LOGITS

MD

2.91

MD

2.74

md

2.45

md

2.36

Md

2.13

Md

1.93

 Maryland

1.59

Maryland

1.38

 Annapolis

1.13

MDL

1.07

Activations Density 0.077%

references to medical degrees, particularly "MD"

No Comments

No Known Activations