INDEX

Explanations

dates in the format of year

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

Przyp

-0.83

Jakie

-0.82

Podob

-0.79

danke

-0.77

Gdzie

-0.77

nasel

-0.77

Zdra

-0.75

Dlaczego

-0.74

Kiedy

-0.72

Jeden

-0.72

POSITIVE LOGITS

 alkoh

1.47

 silikon

1.41

 allarg

1.29

 kön

1.28

(%)

1.28

 vasi

1.28

 makro

1.27

 pól

1.26

 kollek

1.25

 keramik

1.23

Activations Density 0.183%

dates in the format of year

No Comments

No Known Activations