INDEX

Explanations

phrases related to intended goals or objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 بيها

-0.75

bbene

-0.69

 للمعارف

-0.67

 kehadiran

-0.65

 encargada

-0.61

 AssemblyCulture

-0.60

 réguli

-0.59

iteľ

-0.58

thenReturn

-0.57

âmara

-0.57

POSITIVE LOGITS

 purposes

1.57

 reasons

1.36

 Purposes

1.34

purposes

1.19

reasons

1.09

 REASONS

1.09

 Reasons

1.05

REASONS

1.02

 redenen

0.86

Reasons

0.85

Activations Density 0.079%

phrases related to intended goals or objectives

No Comments

No Known Activations