INDEX

Explanations

terms related to medical procedures, diagnoses, and their associated risks or complications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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



-0.74

+#+#

-0.63

servable

-0.58

isielt

-0.52

 Sprecher

-0.52

chymal

-0.51

resiasi

-0.51

 Obrador

-0.50

 actualidad

-0.50

neum

-0.49

POSITIVE LOGITS

 during

3.23

during

2.73

 During

2.55

 DURING

2.50

During

2.48

 durante

2.46

 tijdens

2.20

durante

2.08

Durante

1.98

 durant

1.96

Activations Density 0.871%

terms related to medical procedures, diagnoses, and their associated risks or complications

No Comments

No Known Activations