INDEX

Explanations

numerical measurements related to size and dimensions

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>

-0.71

 picioare

-0.54

Predecesor

-0.53

տ

-0.53

ffè

-0.53

Joseph

-0.51

 împre

-0.50

Vamos

-0.50

퀀

-0.49

 Joey

-0.49

POSITIVE LOGITS

 Depth

0.89

 DEPTH

0.89

 eorum

0.86

 ejus

0.84

 quæ

0.83

 depth

0.82

 maroc

0.81

 trion

0.81

 habet

0.79

 Somal

0.78

Activations Density 0.555%

numerical measurements related to size and dimensions

No Comments

No Known Activations