INDEX

Explanations

occurrences of "en" or "En" and related forms

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

 myſelf

-1.32

 Anſ

-1.29

 itſelf

-1.27

Efq

-1.21

 Majefty

-1.20

 themſelves

-1.20

 ainfi

-1.19

 leſs

-1.18

 ſeveral

-1.17

 Theſe

-1.17

POSITIVE LOGITS

en

3.40

En

3.23

En

3.00

EN

2.70

en

2.36

EN

1.88

én

1.09

enc

1.06

 ен

1.04

enf

1.00

Activations Density 0.070%

occurrences of "en" or "En" and related forms

No Comments

No Known Activations