INDEX

Explanations

phrases or terms indicating relative position or comparison, specifically focusing on the term "above."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Portail

-0.84

 AssemblyCompany

-0.79

 kasarigan

-0.79

man

-0.70

😭😭

-0.69

er

-0.68

pulumi

-0.67

riwal

-0.66

 SqlConnection

-0.66

uParam

-0.66

POSITIVE LOGITS

ABOVE

1.38

 ABOVE

1.36

 BELOW

1.30

 Above

1.19

 Below

1.17

above

1.16

Above

1.15

below

1.14

 above

1.12

 below

1.09

Activations Density 0.074%

phrases or terms indicating relative position or comparison, specifically focusing on the term "above."

No Comments

No Known Activations