INDEX

Explanations

references to law enforcement personnel

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Linq

-0.80

 frattempo

-0.72

 Katal

-0.71

glicher

-0.70

<()>

-0.69

 podido

-0.67

Mog

-0.66

 Burnt

-0.66

Toler

-0.64

place

-0.64

POSITIVE LOGITS

 officers

1.28

officers

1.25

 OFFICERS

1.23

 Officers

1.22

 OFFICER

1.17

Officers

1.16

officer

1.13

 instruments

1.10

 Instruments

1.08

 Officer

1.07

Activations Density 0.102%

references to law enforcement personnel

No Comments

No Known Activations