INDEX

Explanations

medical terms and concepts

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

 ApiService

-0.45

STRACT

-0.43

IMENTAL

-0.42

 contd

-0.42

VIRON

-0.41

 Touchable

-0.41

ellemző

-0.41

CLUSIVE

-0.41

numericUpDown

-0.40

 aliphatic

-0.40

POSITIVE LOGITS

uhr

0.56

sii

0.55

 mitte

0.53

aen

0.52

原始内容存档于

0.50

 anton

0.50

 behar

0.49

 induk

0.49

 kön

0.49

 Kategor

0.48

Activations Density 0.030%

medical terms and concepts

No Comments

No Known Activations