INDEX

Explanations

programming-related keywords and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

and

-0.75

INESS

-0.54

and

-0.50

性和

-0.46

]][

-0.46

Hö

-0.46

setPointSize

-0.46

or

-0.46

ارت

-0.46

 மற்றும்

-0.45

POSITIVE LOGITS

 CreateTagHelper

0.97

 tartalomajánló

0.96

 дописавши

0.88

 oprot

0.88

LookAnd

0.87

saraba

0.84

RenderAtEndOf

0.82

 незавершена

0.81

 kaarangay

0.80

setVerticalGroup

0.79

Activations Density 0.031%

programming-related keywords and concepts

No Comments

No Known Activations