INDEX

Explanations

references to the word "lion."

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 departament

-0.54

cso

-0.54

hek

-0.54

 ché

-0.53

 kras

-0.52

 polie

-0.51

 palet

-0.51

 stok

-0.51

 Verk

-0.51

 lele

-0.50

POSITIVE LOGITS

 Lion

1.45

 lion

1.42

 Lions

1.37

Lion

1.36

 lions

1.33

 LION

1.28

Lions

1.23

lion

0.92

lions

0.89

Leo

0.86

Activations Density 0.127%

references to the word "lion."

No Comments

No Known Activations