INDEX

Explanations

terms related to mutual dependencies and interactions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

twice

-0.56

breit

-0.52

 acert

-0.51

EnumMember

-0.51

ároz

-0.51

 standardize

-0.50

Évaluation

-0.50

WTF

-0.49

conven

-0.48

irage

-0.47

POSITIVE LOGITS

 interdependent

1.28

 interdependence

1.15

 complement

1.14

 complementary

1.10

 interrelated

1.07

 complements

1.00

 Complement

0.99

 synergistic

0.98

 interconnected

0.96

 interacting

0.96

Activations Density 0.567%

terms related to mutual dependencies and interactions in various contexts

No Comments

No Known Activations