INDEX

Explanations

references to excessive amounts or levels of something

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.81

-0.79

ri

-0.74

ur

-0.70

up

-0.69

Portail

-0.66

in

-0.65

<eos>

-0.63

Sit

-0.63

POSITIVE LOGITS

 myſelf

1.51

Efq

1.28

 itſelf

1.25

 poffible

1.23

 ſeveral

1.23

 ſever

1.23

 Monfieur

1.22

 Theſe

1.21

 Excessive

1.19

wiſe

1.16

Activations Density 0.020%

references to excessive amounts or levels of something

No Comments

No Known Activations