INDEX

Explanations

expressions of strong affirmation or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 serem

-0.89

檚

-0.86

themselves

-0.85

 themselves

-0.81

 terem

-0.79

 yourselves

-0.63

OGND

-0.60

herself

-0.58

 numberOfRows

-0.55

rxjs

-0.55

POSITIVE LOGITS

 have

1.15

can

1.11

don

1.10

 cannot

1.07

am

1.06

 want

1.02

 think

0.99

 believe

0.96

 feel

0.96

 wish

0.92

Activations Density 0.062%

expressions of strong affirmation or emphasis

No Comments

No Known Activations