INDEX

Explanations

medical terms related to administering treatments or procedures

oai_token-act-pair · gpt-3.5-turbo

terms related to the act of administering or giving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Â¨

-0.75

faces

-0.72

wi

-0.67

faced

-0.66

itect

-0.65

 Pascal

-0.64

rimp

-0.64

hon

-0.62

 Thief

-0.61

 GÃ¶

-0.61

POSITIVE LOGITS

 administered

1.03

 administering

1.00

 administer

0.95

 drip

0.80

 helicop

0.80

 administ

0.79

 doses

0.78

 dose

0.75

 orally

0.75

utical

0.75

Activations Density 0.033%

medical terms related to administering treatments or procedures

terms related to the act of administering or giving

No Comments

No Known Activations