INDEX

Explanations

medical conditions and terms related to health

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>

-3.18

Geplaatst

-0.70

ⓧ

-0.69

 infar

-0.68

Autoritní

-0.67

 Paglinawan

-0.66

 дописавши

-0.66

adaptiveStyles

-0.65

ɵɵ

-0.64

急性

-0.64

POSITIVE LOGITS

 ecru

1.53

 affor

1.51

 véhic

1.46

 sovere

1.42

hcm

1.42

 Confu

1.40

 soulign

1.39

 disagre

1.39

 Intere

1.37

Juf

1.36

Activations Density 1.229%

medical conditions and terms related to health

No Comments

No Known Activations