INDEX

Explanations

references to time and age, particularly involving years and historical contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.71

Билгалдахарш

-0.70

 ويكيپيديا

-0.65

setDo

-0.64

Filmografie

-0.64

HasIndex

-0.63

CreateIndex

-0.63

AddField

-0.62

toBeDefined

-0.61

ⓧ

-0.60

POSITIVE LOGITS

 ecru

1.64

 milf

1.48

 indestru

1.43

 maneu

1.43

 bordeaux

1.41

 bandung

1.40

 lamborghini

1.39

 nutella

1.38

 paradiso

1.38

 pandan

1.34

Activations Density 0.083%

references to time and age, particularly involving years and historical contexts

No Comments

No Known Activations