INDEX

Explanations

instances of the article "an" and related usages in structured contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Monfieur

-1.39

 myſelf

-1.31

 Theſe

-1.31

 Majefty

-1.28

ſelf

-1.23

 pleaſure

-1.19

Efq

-1.18

 uſe

-1.17

 faſt

-1.17

 neceffary

-1.16

POSITIVE LOGITS

an

0.90

an

0.81

An

0.77

AN

0.73

Al

0.69

 plus

0.61

An

0.60

And

0.59

0.58

sur

0.57

Activations Density 0.296%

instances of the article "an" and related usages in structured contexts

No Comments

No Known Activations