INDEX

Explanations

phrases indicating common occurrence or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Wilber

-0.60

 Azevedo

-0.58

fæ

-0.58

 Zachary

-0.56

 ReactDOM

-0.56

Kingston

-0.56

!("{

-0.56

ειν

-0.55

 Zappa

-0.55

 Kingston

-0.55

POSITIVE LOGITS

 usually

1.17

 Usually

1.06

Usually

1.04

 solito

1.01

usually

0.97

 Normally

0.95

 normally

0.95

 typically

0.94

 Typically

0.93

typically

0.93

Activations Density 0.102%

phrases indicating common occurrence or frequency

No Comments

No Known Activations