INDEX

Explanations

phrases related to technology or technological processes

oai_token-act-pair · gpt-3.5-turbo

instances of strong negative sentiment or criticism

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cumbers

-0.73

 tremend

-0.71

 eleph

-0.71

 engagements

-0.70

 blinded

-0.69

 practition

-0.68

 citiz

-0.67

 misunder

-0.66

awei

-0.66

 mosqu

-0.66

POSITIVE LOGITS

Anyway

1.32

 Anyway

0.99

UPDATE

0.98

Seriously

0.95

ÂłÂłÂł

0.92

ÂłÂłÂłÂłÂłÂłÂłÂł

0.91

Bonus

0.90

Update

0.90

Thankfully

0.90

ÂłÂłÂłÂł

0.90

Activations Density 0.381%

phrases related to technology or technological processes

instances of strong negative sentiment or criticism

No Comments

No Known Activations