INDEX

Explanations

specific named entities or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

vstack

-0.75

 Balboa

-0.73

NFS

-0.72

HZ

-0.71

IsContent

-0.71

RectangleBorder

-0.71

rawDesc

-0.70

 Carra

-0.69

 charset

-0.68

JsonInclude

-0.68

POSITIVE LOGITS

Ey

0.71

 Raton

0.70

Portail

0.68

 Albin

0.68

Choi

0.67

حياته

0.65

Butler

0.64

 primas

0.64

ORMAL

0.64

 Bobby

0.64

Activations Density 0.898%

specific named entities or brands

No Comments

No Known Activations