INDEX

Explanations

specific names and terms associated with individuals or organizations

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

 iſt

-1.18

bootstrapcdn

-1.17

 myſelf

-1.15

 Conſ

-1.15

 ſtate

-1.14

 raiſ

-1.13

Eſ

-1.12

 Reſ

-1.11

 faſt

-1.11

ſelf

-1.10

POSITIVE LOGITS

0.50

Przypisy

0.47

 душ

0.47

0.46

la

0.46

La

0.45

Activations Density 1.081%

specific names and terms associated with individuals or organizations

No Comments

No Known Activations