INDEX

Explanations

references to the name "Robert."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Dinah

-0.73

Jody

-0.71

 سما

-0.69

 yapa

-0.68

zinha

-0.66

 Unwin

-0.64

yethylene

-0.63

IDC

-0.63

 trin

-0.62

вью

-0.61

POSITIVE LOGITS

 Robert

1.95

Robert

1.79

 robert

1.66

 ROBERT

1.66

robert

1.51

ROBERT

1.48

 Rober

1.27

 Roberts

1.20

Bob

1.09

Roberts

1.05

Activations Density 0.072%

references to the name "Robert."

No Comments

No Known Activations