INDEX

Explanations

transitions or logical conclusions in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

man

-0.66

 τά

-0.61

dag

-0.60

hol

-0.60

ing

-0.59

 grze

-0.57

łucha

-0.56

cing

-0.56

cy

-0.55

 Cæsar

-0.55

POSITIVE LOGITS

Therefore

1.03

 therefore

1.03

+#+

1.01

theless

1.00

 therefor

1.00

 Therefore

1.00

FieldDescriptor

0.92

Hence

0.88

 propOrder

0.87

+#+#

0.87

Activations Density 0.128%

transitions or logical conclusions in the text

No Comments

No Known Activations