INDEX

Explanations

references to specific processes, actions, or items within various contexts, often pertaining to scientific or legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

uxxxx

-0.82

 '\\;'

-0.79

SequentialGroup

-0.72

хьтан

-0.68

complexContent

-0.65

ंदीखरीदारी

-0.65

뀐

-0.65

rungsseite

-0.64

ChildScrollView

-0.64

 avoient

-0.63

POSITIVE LOGITS

1.16

or

1.08

 или

0.72

0.71

 یا

0.70

หรือ

0.70

或

0.69

 atau

0.66

bzw

0.61

や

0.61

Activations Density 0.925%

references to specific processes, actions, or items within various contexts, often pertaining to scientific or legal terminology

No Comments

No Known Activations