INDEX

Explanations

instances of the word "where."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

reactstrap

-0.73

طيع

-0.64

jface

-0.59

windowFixed

-0.58

Doris

-0.54

 cyst

-0.53

ApiModelProperty

-0.52

 Huff

-0.52

 Gaff

-0.52

faits

-0.52

POSITIVE LOGITS

 where

3.01

Where

3.01

 Where

2.98

where

2.83

 WHERE

2.56

WHERE

2.47

 donde

2.06

Donde

2.01

 Donde

1.99

où

1.97

Activations Density 0.097%

instances of the word "where."

No Comments

No Known Activations