INDEX

Explanations

specific formatting elements and numerical indicators often used in computational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 lenker

-0.67

SceneManagement

-0.64

antMatchers

-0.63

buttonShape

-0.57

ThroughAttribute

-0.56

 بيها

-0.55

rostis

-0.52

FormTagHelper

-0.50

 stdClass

-0.50

hatan

-0.50

POSITIVE LOGITS

webElementGuid

0.70

цездатний

0.68

AndEndTag

0.65

 دیکھیے

0.59

jsxFileName

0.58

 rospy

0.57

PreferredItem

0.53

InjectAttribute

0.51

curité

0.50

 <=",

0.49

Activations Density 0.686%

specific formatting elements and numerical indicators often used in computational contexts

No Comments

No Known Activations