INDEX

Explanations

medical conditions and treatment-related terms

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>

-2.51

/***

-0.65

///////////

-0.64

displayquote

-0.59

 remet

-0.59

///////////////

-0.59

 naudoti

-0.58

 mena

-0.57

//////////////

-0.56

////////////

-0.55

POSITIVE LOGITS

 swarovski

0.98

 destinées

0.95

 ecru

0.92

 useRouter

0.91

 actionTypes

0.91

 sappi

0.89

 eduardo

0.89

 unlaw

0.88

 chrysler

0.87

 conç

0.85

Activations Density 1.694%

medical conditions and treatment-related terms

No Comments

No Known Activations