INDEX

Explanations

graphical or data representation elements, particularly in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

CppMethod

-0.60

GeneratedMessage

-0.56

 تضيفلها

-0.51

 insuffisamment

-0.50

 torchvision

-0.50

 Kết

-0.50

sumoto

-0.49

pran

-0.49

wyżs

-0.48

 kết

-0.48

POSITIVE LOGITS

 مرئيه

0.73

selectAll

0.71

classed

0.67

routeProvider

0.54

 selectAll

0.50

 chlorine

0.50

dshaw

0.49

portál

0.49

 "..\..\

0.49

uthor

0.47

Activations Density 0.111%

graphical or data representation elements, particularly in coding contexts

No Comments

No Known Activations