INDEX

Explanations

instances of the word "little."

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 quæ

-0.69

 незавершена

-0.67

RectangleBorder

-0.67

何より

-0.65

 gynnwys

-0.64

 كومونز

-0.63

 ujednoznacz

-0.62

//

-0.61

 ainfi

-0.61

TypedDataSet

-0.59

POSITIVE LOGITS

bit

2.13

bit

1.35

Bit

1.24

Bit

1.20

BIT

1.16

 bits

1.15

 bisschen

0.99

bits

0.99

BIT

0.95

 beetje

0.94

Activations Density 0.044%

instances of the word "little."

No Comments

No Known Activations