INDEX

Explanations

phrases where someone is strongly advocating for something, often emphasizing the importance of action, testing, or further investigation

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>

-1.27

 apprehen

-0.99

 repug

-0.83

 inconce

-0.77

/***

-0.75

 ingrat

-0.73

Fré

-0.69

 disagre

-0.68

 reconno

-0.67

POSITIVE LOGITS

 insist

0.91

 insisted

0.84

 insists

0.80

 ASSERT

0.79

 insisting

0.78

 asserted

0.75

 assertion

0.75

 assert

0.74

 Assert

0.74

 insistence

0.73

Activations Density 0.269%

phrases where someone is strongly advocating for something, often emphasizing the importance of action, testing, or further investigation

No Comments

No Known Activations