INDEX

Explanations

terms associated with precision and quality improvements in tools or methods

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

rungsseite

-0.97

Personensuche

-0.76

 '\\;'

-0.69

новниш

-0.69

GraphicsUnit

-0.67

 MainAxisSize

-0.65

 Wikispecies

-0.65

mybatisplus

-0.63

FirebaseDatabase

-0.61

 BrowserModule

-0.59

POSITIVE LOGITS

 refinement

1.19

 refine

1.10

 refined

1.03

 refinements

1.03

 refining

1.01

 sharpening

0.97

 sharpen

0.97

 polished

0.96

 Refin

0.95

 sharpened

0.93

Activations Density 0.389%

terms associated with precision and quality improvements in tools or methods

No Comments

No Known Activations