INDEX

Explanations

references to the color brown

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciutto

-0.77

+#+#

-0.77

TextInputLayout

-0.75

MessageTagHelper

-0.74

:✨

-0.73

벤트

-0.72

ropractic

-0.72

&:

-0.70

 Winaray

-0.70

στι

-0.69

POSITIVE LOGITS

 Brown

2.37

Brown

2.25

 brown

2.23

 BROWN

2.12

brown

2.05

BROWN

2.00

 browns

1.79

 Browns

1.75

 browned

1.42

 brownish

1.40

Activations Density 0.022%

references to the color brown

No Comments

No Known Activations