INDEX

Explanations

phrases that express totality or completeness

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

Follows "completely" and describes an opinion

np_acts-logits-general · gemini-2.0-flash

completely + descriptive word

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

 Slightly

-0.73

 slightly

-0.73

slightly

-0.71

 somewhat

-0.70

Slightly

-0.69

somewhat

-0.66

 very

-0.66

AddHtmlAttribute

-0.65

 agak

-0.64

 really

-0.63

POSITIVE LOGITS

IGraphics

0.72

 utafitiHapana

0.72

tly

0.59

Composable

0.59

dientemente

0.58

летия

0.58

 different

0.57

 unrelated

0.57

不同

0.56

 consultato

0.56

Activations Density 0.122%

phrases that express totality or completeness

Follows "completely" and describes an opinion

completely + descriptive word

No Comments

No Known Activations