INDEX

Explanations

terms and phrases related to user interface components and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CppMethod

-1.15

LookAnd

-1.13

GraphicsUnit

-1.11

DockStyle

-1.09

DeleteBehavior

-1.04

#+#

-1.04

SharedDtor

-1.03

RegistryLite

-1.02

WebVitals

-1.02

AndEndTag

-1.02

POSITIVE LOGITS

↵

0.56

ck

0.47

0.44

for

0.43

van

0.42

ble

0.41

↵↵

0.41

<eos>

0.41

Activations Density 0.486%

terms and phrases related to user interface components and interactions

No Comments

No Known Activations