INDEX

Explanations

references to events or gatherings happening in a specific location

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

•Test List With Features

No Comments

Negative Logits

<bos>

-1.82

Vegeu

-0.91

ždý

-0.62

Externé

-0.61

Conteúdo

-0.60

Vanjske

-0.60

/***

-0.59

 בְּ

-0.58

película

-0.58

Carreira

-0.58

POSITIVE LOGITS

 Reception

1.33

 reception

1.32

reception

1.25

 receptions

1.22

Reception

1.17

 RECE

1.16

 receptionist

1.04

 tucson

1.04

 jaya

0.99

 receivers

0.99

Activations Density 0.235%

references to events or gatherings happening in a specific location

No Comments

No Known Activations