INDEX

Explanations

elements related to Twitter API processes and user interactions

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

 Portail

-0.74

 ujednoznacz

-0.67

хьтан

-0.60

cipar

-0.59

Portail

-0.58

Spoljašnje

-0.58

 HasFactory

-0.57

 VizieR

-0.56

GIVEREF

-0.55

hnia

-0.54

POSITIVE LOGITS

 tweet

2.09

 tweets

2.01

 Twitter

2.00

 tweeting

1.93

 tweeted

1.91

 Tweet

1.86

 Tweets

1.82

 twitter

1.80

Twitter

1.75

Tweet

1.70

Activations Density 0.195%

elements related to Twitter API processes and user interactions

No Comments

No Known Activations