INDEX

Explanations

terms related to legal actions and medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 ExecuteAsync

-0.71

 vectorielles

-0.55

 dévelo

-0.53

 PackageManager

-0.53

Билгалдахарш

-0.51

 تضيفلها

-0.50

.*")]

-0.50

NullCheck

-0.48

 Padova

-0.47

enciaga

-0.47

POSITIVE LOGITS

 ModelExpression

0.61

+#+#

0.58

colgroup

0.58

 thiệu

0.57

CGPoint

0.56

 totalling

0.54

 fireplace

0.54

 поводу

0.52

protoimpl

0.50

HasKey

0.49

Activations Density 1.041%

terms related to legal actions and medical contexts

No Comments

No Known Activations