INDEX

Explanations

locations and dates in news articles

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

Wię

-0.87

Bardzo

-0.84

Może

-0.81

Și

-0.81

sólo

-0.79

Przyp

-0.77

Dziękuję

-0.77

Obrigado

-0.76

Jako

-0.75

Więcej

-0.75

POSITIVE LOGITS

 gend

1.32

 bett

1.30

mef

1.29

 exem

1.29

 profi

1.29

 wien

1.29

 inder

1.27

 laun

1.24

 embra

1.24

daf

1.24

Activations Density 0.189%

locations and dates in news articles

No Comments

No Known Activations