INDEX

Explanations

references to counting or enumerating

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

The token "count" or "counter"

np_acts-logits-general · gemini-2.0-flash

Count followed by Roman numerals

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

Geplaatst

-0.71

WEBPACK

-0.62

 esternos

-0.61

Rujuakan

-0.61

StateException

-0.55

 Мексичка

-0.55

AppendLine

-0.55

Portail

-0.53

 الحره

-0.53

MemoryWarning

-0.53

POSITIVE LOGITS

 Counts

0.82

 counts

0.80

counts

0.76

setCount

0.71

 totalCount

0.69

downs

0.69

enance

0.68

 Countess

0.67

 COUNT

0.67

Counts

0.65

Activations Density 0.133%

references to counting or enumerating

The token "count" or "counter"

Count followed by Roman numerals

No Comments

No Known Activations