INDEX

Explanations

specific scientific or technical terms and identifiers, particularly in the context of research or data analysis

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 păr

-0.70

 pracowników

-0.68

등학교

-0.67

 singur

-0.67

@"/

-0.66

viedo

-0.66

kommen

-0.66

 campana

-0.64

ló

-0.64

POSITIVE LOGITS

1.24

rz

1.19

zzz

1.18

RZ

1.15

 Lizzy

1.14

iz

1.12

zo

1.12

zz

1.11

zzzz

1.11

Kuz

1.10

Activations Density 1.465%

specific scientific or technical terms and identifiers, particularly in the context of research or data analysis

No Comments

No Known Activations