INDEX

Explanations

mentions and links related to Twitter

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

makeConstraints

-0.80

ValueGeneration

-0.74

SceneManagement

-0.69

Portail

-0.69

 Roskov

-0.69

enderror

-0.68

 gainera

-0.66

 nakalista

-0.63

 ostavi

-0.62

QRect

-0.61

POSITIVE LOGITS

 Twitter

2.05

 tweets

2.01

 tweet

1.83

 Tweets

1.81

Twitter

1.79

 twitter

1.77

 tweeted

1.74

 tweeting

1.73

 TWITTER

1.67

twitter

1.64

Activations Density 0.036%

mentions and links related to Twitter

No Comments

No Known Activations