INDEX

Explanations

proper nouns

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>

-2.30

zają

-0.72

ząca

-0.69

zonego

-0.69

queryInterface

-0.66

zące

-0.65

/*++

-0.64

Pozri

-0.62

AsUp

-0.62

ząc

-0.60

POSITIVE LOGITS

 Abbé

1.21

 emphat

1.20

 effe

1.19

 maneu

1.19

 excru

1.15

 increa

1.14

 inev

1.14

 juven

1.13

 unwarran

1.13

 desir

1.12

Activations Density 0.345%

proper nouns

No Comments

No Known Activations