INDEX

Explanations

references to brands and brand loyalty

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

brands and rebranding

np_acts-logits-general · gemini-2.0-flash

branding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ucchini

-0.52

 devoirs

-0.49

tomy

-0.48

AccessFile

-0.48

hio

-0.47

Skocz

-0.46

 Ditto

-0.46

Ditto

-0.45

 computation

-0.45

粟

-0.45

POSITIVE LOGITS

 BRAND

1.12

Brand

1.10

 brand

1.10

 Brand

1.06

BRAND

1.00

Brands

0.99

brand

0.98

 brands

0.95

 Brands

0.94

brands

0.94

Activations Density 0.056%

references to brands and brand loyalty

brands and rebranding

branding

No Comments

No Known Activations