INDEX

Explanations

dates formatted as month/day/year

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>

-2.58

<?

-1.16

ⓧ

-1.12

-1.10

/**

-1.02

<?

-0.93

/***

-0.79

endwhile

-0.72

 disbur

-0.70

 springfox

-0.69

POSITIVE LOGITS

()/

0.88

 thuy

0.83

 quoc

0.82

 marte

0.81

²/

0.81

 corrom

0.81

0.80

 Trasp

0.79

 keramik

0.79

 maksi

0.78

Activations Density 0.216%

dates formatted as month/day/year

No Comments

No Known Activations