INDEX

Explanations

titles and ranks associated with military personnel

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ſelf

-0.96



-0.84

 itſelf

-0.82

</caption>

-0.81

 ويكيميديا

-0.79

ſelves

-0.78

reszcie

-0.77

pezifische

-0.76

etheless

-0.76

horabuena

-0.75

POSITIVE LOGITS

 General

2.13

General

1.77

 GENERAL

1.25

 Generals

1.20

Gen

1.08

 Général

1.05

GENERAL

1.02

Gen

0.96

 Генера

0.89

 Generale

0.88

Activations Density 0.207%

titles and ranks associated with military personnel

No Comments

No Known Activations