INDEX

Explanations

references to characters or entities associated with power or authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

BeginContext

-0.62

Owner

-0.61

 landlord

-0.60

 Owner

-0.60

 proprietor

-0.59

BuildContext

-0.58

 owner

-0.57

Демографія

-0.57

 Owners

-0.57

 grandparents

-0.57

POSITIVE LOGITS

 assistants

1.13

 assistant

1.08

 subordinates

0.99

 aides

0.94

 followers

0.93

 subordinate

0.93

 disciples

0.92

 aide

0.91

 disciple

0.91

 minions

0.90

Activations Density 0.345%

references to characters or entities associated with power or authority

No Comments

No Known Activations