INDEX

Explanations

words related to suffering and medical conditions

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "suffering from" followed by various conditions or ailments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

iture

-0.75

Commerce

-0.73

orah

-0.72

prints

-0.69

nels

-0.67

hee

-0.65

amation

-0.65

retty

-0.65

ħĭ

-0.64

ongyang

-0.64

POSITIVE LOGITS

 acute

0.89

 illness

0.84

 injuries

0.80

 ailments

0.78

 suff

0.78

 recovering

0.77

 childbirth

0.75

 trauma

0.74

 malnutrition

0.73

 patients

0.72

Activations Density 0.115%

words related to suffering and medical conditions

instances of the phrase "suffering from" followed by various conditions or ailments

No Comments

No Known Activations