INDEX

Explanations

phrases related to user experiences or sentiments regarding products or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

xim

-0.41

enderror

-0.36

Referencer

-0.36

 excluded

-0.35

جغرافيا

-0.35

 eventual

-0.35

meg

-0.35

 فان

-0.34

 StringTokenizer

-0.34

 launching

-0.34

POSITIVE LOGITS

again

0.71

 AGAIN

0.67

 novamente

0.66

 again

0.64

Again

0.63

 ponownie

0.62

 nuevamente

0.61

 nuovamente

0.60

 opnieuw

0.60

 erneut

0.59

Activations Density 0.579%

phrases related to user experiences or sentiments regarding products or media

No Comments

No Known Activations