INDEX

Explanations

phrases related to the effects or impacts of actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ⓧ

-0.70

<bos>

-0.58

WebVitals

-0.56

+#+#

-0.54

 Савезне

-0.53

VertexAttrib

-0.52

كويكب

-0.51

Бахар

-0.50

RunWith

-0.50

少了

-0.49

POSITIVE LOGITS

 profound

0.64

 measurable

0.64

 nonatomic

0.62

 significant

0.59

 huge

0.58

 appreciable

0.56

 besar

0.56

 positive

0.56

 demonstra

0.56

 tremendous

0.55

Activations Density 0.241%

phrases related to the effects or impacts of actions or events

No Comments

No Known Activations