INDEX

Explanations

references to leadership qualities and styles

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

"leadership" followed by a style or ranking

np_acts-logits-general · gemini-2.0-flash

leadership styles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 convertView

-0.56

criminate

-0.56

wst

-0.50

اریخ

-0.50

könig

-0.48

ENDIAN

-0.48

 izquierdo

-0.47

╔

-0.47

 prawda

-0.47

aguya

-0.47

POSITIVE LOGITS

Hentet

0.81

hips

0.79

 roles

0.75

SourceChecksum

0.72

 leadership

0.69

 role

0.68

Leadership

0.62

 qualities

0.62

IVEREF

0.61

azgo

0.61

Activations Density 0.117%

references to leadership qualities and styles

"leadership" followed by a style or ranking

leadership styles

No Comments

No Known Activations