INDEX

Explanations

phrases related to political processes such as elections, nominations, caucuses, conventions, delegates, and the constitution

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>

-0.95

 Simplemente

-0.54

 intersper

-0.53

aui

-0.52

Caratter

-0.51

 CascadeType

-0.50

zeg

-0.50

 recast

-0.49

 mobilize

-0.48

 Heff

-0.48

POSITIVE LOGITS

 Delegate

0.83

delegate

0.78

 delegate

0.77

 Delegates

0.77

 delegates

0.70

Delegate

0.69

Glenn

0.69

 Pole

0.68

 Glenn

0.68

 delegation

0.68

Activations Density 0.523%

phrases related to political processes such as elections, nominations, caucuses, conventions, delegates, and the constitution

No Comments

No Known Activations