INDEX

Explanations

references to products, services, companies and activities related to specific brands or businesses

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

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.78

ⓧ

-0.78

 cede

-0.55

 disbur

-0.53

 attesa

-0.53

 standardize

-0.53

šech

-0.52

 harmonize

-0.51

rollment

-0.51

POSITIVE LOGITS

Qu

1.29

Qu

1.21

QU

1.18

qu

1.13

QU

1.05

 Quil

1.03

qu

1.02

 Quin

0.98

 Quar

0.95

Qui

0.95

Activations Density 0.372%

references to products, services, companies and activities related to specific brands or businesses

No Comments

No Known Activations