INDEX

Explanations

coding structures used to access and manipulate data in lists or arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

WriteBarrier

-0.75

principalTable

-0.72

ंदीखरीदारी

-0.70

verifyException

-0.67

RenderAtEndOf

-0.66

انيف

-0.66

 المعيارى

-0.65

PerformLayout

-0.64

rawDesc

-0.64

windowFixed

-0.63

POSITIVE LOGITS

 item

1.07

0.90

item

0.88

0.77

 element

0.68

0.62

 Item

0.61

elem

0.60

0.59

Activations Density 0.501%

coding structures used to access and manipulate data in lists or arrays

No Comments

No Known Activations