INDEX

Explanations

mentions of leadership roles, specifically "boss."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ReusableCell

-0.64

hyd

-0.57

 getField

-0.55

tet

-0.55

LLYWOOD

-0.54

dür

-0.54

amkeit

-0.54

 Quad

-0.54

anwal

-0.54

Aan

-0.53

POSITIVE LOGITS

 bosses

1.32

 boss

1.26

 BOSS

1.21

Chris

1.20

 Chris

1.18

boss

1.11

Boss

1.09

 Boss

1.09

 chris

1.06

BOSS

1.02

Activations Density 0.094%

mentions of leadership roles, specifically "boss."

No Comments

No Known Activations