INDEX

Explanations

terms that relate to the accuracy of information

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.24

 endow

-0.80

 mobilize

-0.78

ⓧ

-0.76

 intersper

-0.75

 disbur

-0.72

 defray

-0.71

 hasten

-0.68

 endeavored

-0.66

żdy

-0.66

POSITIVE LOGITS

Accurate

1.25

 bandung

1.22

 ACCUR

1.19

 sentra

1.17

 accuracy

1.15

 Accuracy

1.15

 ananas

1.15

 lele

1.14

accurate

1.14

 saar

1.13

Activations Density 0.097%

terms that relate to the accuracy of information

No Comments

No Known Activations