INDEX

Explanations

references to government officials and positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 Gracie

-0.78

 esternos

-0.76

 Rass

-0.75

pne

-0.71

CFP

-0.69

AAB

-0.67

 estekak

-0.66

ruptcy

-0.65

gri

-0.65

 UCLA

-0.64

POSITIVE LOGITS

 ministers

1.36

 ministries

1.25

 Ministers

1.23

 Ministry

1.10

 ministry

1.08

 MINISTER

1.05

 Minister

1.05

 MINISTRY

1.04

 Minist

1.02

 ministres

1.02

Activations Density 0.047%

references to government officials and positions

No Comments

No Known Activations

references to government officials and positions

No Comments

No Known Activations