INDEX

Explanations

evaluative descriptors related to quality and aesthetics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

OFFICIAL

-0.48

itario

-0.43

 Misalnya

-0.43

必要がある

-0.43

lasma

-0.43

ordano

-0.43

idal

-0.42

wage

-0.41

 offending

-0.41

 branche

-0.41

POSITIVE LOGITS

 fantastic

0.93

 beautiful

0.89

 amazing

0.88

 terrific

0.87

 wonderful

0.86

 brilliant

0.86

fantastic

0.86

 excellent

0.85

beautiful

0.83

wonderful

0.83

Activations Density 0.189%

evaluative descriptors related to quality and aesthetics

No Comments

No Known Activations