INDEX

Explanations

terms and concepts related to food ingredients and nutritional information

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

due to, consequence, limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 […]

-1.02

↵

-0.97

↵↵

-0.87

<eos>

-0.85

-\\

-0.84

,...

-0.75

,\\

-0.74

-...

-0.71

...

-0.69

 [...]

-0.68

POSITIVE LOGITS

AddTagHelper

0.69

 myſelf

0.65

$_"

0.65

-------------</

0.57

 الحره

0.56

(\<

0.55

$_(

0.54

parsedMessage

0.54

 itſelf

0.53

IGraphics

0.53

Activations Density 1.661%

terms and concepts related to food ingredients and nutritional information

due to, consequence, limitations

No Comments

No Known Activations