INDEX

Explanations

references to the word "Les."

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.59

/**

-0.79

<?

-0.77

 Quoi

-0.74

 Aún

-0.72

-0.69

 Aucune

-0.69

 Autre

-0.68

jątk

-0.67

 Celui

-0.67

POSITIVE LOGITS

Les

1.29

LES

1.15

Les

1.13

les

1.06

 hina

1.03

 saar

1.02

les

0.96

Las

0.95

 magis

0.94

sii

0.91

Activations Density 0.080%

references to the word "Les."

No Comments

No Known Activations