INDEX

Explanations

code-related definitions and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Italijani

-0.89

LookAnd

-0.86

RenderAtEndOf

-0.74

 defStyleAttr

-0.72

richTextPanel

-0.72

 Baillargeon

-0.71

 gynhyrchwyd

-0.71

MessageTagHelper

-0.70

 invokingState

-0.70

تقاوى

-0.70

POSITIVE LOGITS

newcommand

1.47

def

0.73

 cref

0.61

renewcommand

0.55

basicConfig

0.53

openzeppelin

0.53

 CreateTagHelper

0.52

www

0.50

def

0.50

AddWithValue

0.49

Activations Density 0.071%

code-related definitions and keywords

No Comments

No Known Activations