INDEX

Explanations

references to principal positions or entities

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

 philanth

-1.01

 pamph

-1.01

 McLaugh

-0.98

 superintend

-0.97

 reluct

-0.95

 Jara

-0.94

 Alejandra

-0.94

 Bartholo

-0.93

 benevol

-0.93

 créateur

-0.90

POSITIVE LOGITS

 principal

1.33

principal

1.30

Principal

1.26

 Principal

1.23

 principals

1.01

 PRINCIPAL

1.00

cipal

0.88

Princip

0.74

PRINCIP

0.71

 Principals

0.69

Activations Density 0.302%

references to principal positions or entities

No Comments

No Known Activations