INDEX

Explanations

quantifiers that indicate large quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

AfterClass

-0.81

FLA

-0.72

AdapterView

-0.70

</b>

-0.67

 dovrebbero

-0.65

Fla

-0.63

Beats

-0.63

<i>

-0.61

oz

-0.59

 totales

-0.59

POSITIVE LOGITS

MANY

1.60

 MANY

1.57

 many

1.50

many

1.31

 Many

1.24

Many

1.14

 muchos

1.07

Muchos

0.99

NUMX

0.98

Cuántos

0.97

Activations Density 0.064%

quantifiers that indicate large quantities

No Comments

No Known Activations