INDEX

Explanations

phrases describing written work or publications, as well as specific financial terms

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>

-2.50

 benevol

-0.96

 intersper

-0.95

ⓧ

-0.95

 racon

-0.91

/***

-0.90

 hentai

-0.86

 pessi

-0.86

 inconce

-0.85

POSITIVE LOGITS

...

0.80

…

0.73

...

0.67

....

0.63

…

0.62

..."

0.61

..

0.57

…”

0.57

….

0.57

ChatColor

0.56

Activations Density 0.100%

phrases describing written work or publications, as well as specific financial terms

No Comments

No Known Activations