INDEX

Explanations

terms and phrases that indicate distinctions or comparisons between entities or concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Coolidge

-0.88

PhysRev

-0.86

 Manpower

-0.85

Sagittarius

-0.82

 Wallis

-0.81

 Ayer

-0.81

 Mehdi

-0.79

 headers

-0.79

 Camel

-0.79

 Rosal

-0.78

POSITIVE LOGITS

 distinguish

1.31

distingu

1.24

 Dist

1.24

 distingu

1.20

DIST

1.20

 distingue

1.19

 disting

1.19

 DIST

1.18

dist

1.18

 distinguishes

1.14

Activations Density 0.122%

terms and phrases that indicate distinctions or comparisons between entities or concepts

No Comments

No Known Activations