INDEX

Explanations

instances of the word "have" and its variations indicating possession or necessity

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

PRNewswire

-0.68

⋙

-0.68

 recognizes

-0.63

IntoConstraints

-0.59

 groaning

-0.58

setVerticalGroup

-0.58

binden

-0.56

preprint

-0.56

Ja

-0.56

')['

-0.56

POSITIVE LOGITS

Have

1.69

 Have

1.48

HAVE

1.25

have

1.10

 HAVE

0.85

ſelf

0.78

 purpoſe

0.76

 pleaſure

0.74

 poffible

0.73

 ſtand

0.72

Activations Density 0.129%

instances of the word "have" and its variations indicating possession or necessity

No Comments

No Known Activations