INDEX

Explanations

terms and phrases related to programming and data transformation using APIs and libraries

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

 πως

-1.10

 illetve

-1.08

vrigt

-1.05

omiast

-1.02

 gjerne

-0.93

 pues

-0.92

 sämtliche

-0.90

 hiszen

-0.89

 dessutom

-0.89

 tevens

-0.89

POSITIVE LOGITS

 XNUMX

1.51

1.15

NUMX

0.91

.;

0.85

0.84

™

0.81

̵

0.74

 itſelf

0.71

.:

0.63

🇧

0.62

Activations Density 0.068%

terms and phrases related to programming and data transformation using APIs and libraries

No Comments

No Known Activations