INDEX

Explanations

occurrences of hashtags in text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

trouble

-0.52

miljø

-0.48

šić

-0.48

λέ

-0.47

amaño

-0.45

antity

-0.43

 τί

-0.43

 flin

-0.43

arrête

-0.42

witched

-0.41

POSITIVE LOGITS

 EconPapers

0.97

 AssemblyTitle

0.94

expandindo

0.93

例文帳に追加

0.85

❋

0.82

 ostavi

0.81

SharedCtor

0.81

 Pingback

0.81

InjectAttribute

0.80

 <=",

0.78

Activations Density 0.149%

occurrences of hashtags in text

No Comments

No Known Activations