INDEX

Explanations

scientific and medical terms related to substances, reactions, or conditions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

terms related to marine toxins and their health effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 Â»

-0.76

>)

-0.73

 WEEK

-0.70

SHARE

-0.69

pic

-0.68

 PHOTO

-0.67

BUS

-0.66

 âĢ¦"

-0.64

 Pinterest

-0.63

 JACK

-0.62

POSITIVE LOGITS

,[

2.79

.[

2.77

".[

2.57

).[

2.39

."[

2.37

:[

2.26

2.19

)[

1.98

][

1.68

[/

1.67

Activations Density 0.694%

scientific and medical terms related to substances, reactions, or conditions

terms related to marine toxins and their health effects

No Comments

No Known Activations