INDEX

Explanations

questions and uncertainties regarding identification or clarity

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

uncertainty, not knowing, possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.73

хьтан

-0.73

 nakalista

-0.69

 betweenstory

-0.65

✨:

-0.62

 kasarigan

-0.60

 盗撮

-0.57

kháu

-0.57

Rhestr

-0.56

[@BOS@]

-0.55

POSITIVE LOGITS

 incertidumbre

0.53

 whether

0.49

 unknown

0.49

 uncertain

0.47

 uncertainty

0.44

 unclear

0.43

 unsure

0.42

 UNKNOWN

0.41

 undefined

0.41

不知道

0.40

Activations Density 0.070%

questions and uncertainties regarding identification or clarity

uncertainty, not knowing, possibilities

No Comments

No Known Activations