INDEX

Explanations

discussions or mentions of technical concepts and terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

sizeCache

-0.68

 BorderRadius

-0.68

MeasureSpec

-0.67

antMatchers

-0.66

ZoneId

-0.65

Havolalar

-0.65

MessageTagHelper

-0.64

RequestMapping

-0.62

AddTagHelper

-0.60

GEBURTSDATUM

-0.60

POSITIVE LOGITS

ities

1.12

TECHNICAL

0.73

ity

0.72

 technical

0.65

technical

0.62

 facie

0.59

 ***/

0.59

 Technical

0.59

Technical

0.58

 TECHNICAL

0.57

Activations Density 0.102%

discussions or mentions of technical concepts and terms

No Comments

No Known Activations