INDEX

Explanations

phrases that express opinions on clarity and transparency in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 nemlig

-0.52

なんですよ

-0.51

なのです

-0.50

 totiž

-0.49

يكب

-0.48

 beginnetje

-0.48

んだよ

-0.45

なのだ

-0.45

んだよね

-0.44

orsese

-0.43

POSITIVE LOGITS

 obvious

2.54

obvious

2.32

 obviously

2.10

obviously

2.08

Obvious

2.03

 obvio

1.91

 Obviously

1.86

Obviously

1.80

duh

1.72

duh

1.67

Activations Density 0.405%

phrases that express opinions on clarity and transparency in communication

No Comments

No Known Activations