INDEX

Explanations

words related to physical wounds and injuries

oai_token-act-pair · gpt-3.5-turbo

references to wounds and their healing processes

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

Negative Logits

*/(

-0.80

soDeliveryDate

-0.75

 GEAR

-0.73

sat

-0.71

rador

-0.71

ructose

-0.71

hare

-0.66

role

-0.65

entric

-0.65

essions

-0.65

POSITIVE LOGITS

 wounds

1.59

 healed

1.19

 wound

1.18

 inflicted

1.13

 heals

1.07

 healing

1.06

 heal

1.06

 wounded

1.00

 scars

0.99

 sore

0.95

Activations Density 0.053%

words related to physical wounds and injuries

references to wounds and their healing processes

No Known Activations