INDEX

Explanations

questions and statements about personal experiences and emotions

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

Followed by discourse markers

np_acts-logits-general · gemini-2.0-flash

well, honestly, hmm

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 tambin

-0.56

 inoltre

-0.52

 asimismo

-0.51

それでも

-0.50

 nevertheless

-0.50

 tetapi

-0.49

anmoins

-0.49

 typelib

-0.48

 kuitenkin

-0.48

 dessutom

-0.48

POSITIVE LOGITS

Well

0.62

Honestly

0.62

Hmmm

0.61

Hmm

0.59

 Hmmm

0.59

 Honestly

0.58

Hmm

0.58

hmm

0.58

 Well

0.58

うーん

0.57

Activations Density 0.248%

questions and statements about personal experiences and emotions

Followed by discourse markers

well, honestly, hmm

No Comments

No Known Activations