INDEX

Explanations

phrases related to health benefits or medicinal properties

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.14

天

-0.59

 Team

-0.58

 thuận

-0.57

Team

-0.56

 himo

-0.56

 đãi

-0.56

card

-0.55

Mediabestanden

-0.55

POSITIVE LOGITS

 disreg

1.31

 reluct

1.26

 dises

1.26

 maneu

1.22

Juf

1.21

 chong

1.19

hcm

1.17

 intermitt

1.17

 lele

1.15

 jurassic

1.14

Activations Density 0.534%

phrases related to health benefits or medicinal properties

No Comments

No Known Activations