INDEX

Explanations

repeated mentions of the word "each"

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

SUT

-0.71

er

-0.66

Goy

-0.66

Klo

-0.62

Cof

-0.60

 Bons

-0.60

Lol

-0.59

Lol

-0.58

buster

-0.58

able

-0.57

POSITIVE LOGITS

EACH

1.50

 EACH

1.36

 each

1.24

each

1.21

 Each

1.19

Each

1.15

BeforeEach

1.14

각

1.11

masing

1.10

Chaque

1.07

Activations Density 0.065%

repeated mentions of the word "each"

No Comments

No Known Activations