INDEX

Explanations

terms related to medical conditions and treatments involving inflammation or acute situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 russes

-0.80

 vertes

-0.78

 latine

-0.74

 chré

-0.71

twimg

-0.70

 wierd

-0.70

 charité

-0.70

utilisons

-0.70

 connues

-0.69

 marins

-0.69

POSITIVE LOGITS

Legături

0.62

StoryboardSegue

0.57

cu

0.55

0.54

0.53

 ujednoznacz

0.51

are

0.49

can

0.49

ge

0.49

 question

0.48

Activations Density 0.063%

terms related to medical conditions and treatments involving inflammation or acute situations

No Comments

No Known Activations