INDEX

Explanations

instances of the word "let" in various formats

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

Follows "Let" or "Let's"

np_acts-logits-general · gemini-2.0-flash

phrases starting with "Let"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ContentValues

-0.58

istán

-0.58

 Sequo

-0.57

standers

-0.56

EndContext

-0.55

:✨

-0.55

PreferredItem

-0.54

 susun

-0.53

المراجع

-0.53

Threading

-0.53

POSITIVE LOGITS

us

0.68

’

0.65

0.62

Lets

0.61

let

0.60

Let

0.59

 Lets

0.58

 lets

0.55

me

0.54

 дописавши

0.53

Activations Density 0.090%

instances of the word "let" in various formats

Follows "Let" or "Let's"

phrases starting with "Let"

No Comments

No Known Activations