INDEX

Explanations

expressions of care and compassion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

HtmlAttribute

-0.64

Watson

-0.44

 BoxFit

-0.44

hånd

-0.43

 commission

-0.43

 fontWeight

-0.43

řen

-0.42

Eli

-0.42

</

-0.41

POSITIVE LOGITS

 &___

0.85

 CURIAM

0.80

nonumber

0.78

Życiorys

0.69

 bounded

0.69

 kasarigan

0.68

 caring

0.68

atoires

0.67

 Guides

0.66

parametrize

0.66

Activations Density 0.087%

expressions of care and compassion

No Comments

No Known Activations