INDEX

Explanations

descriptions of injuries and medical conditions

oai_token-act-pair · gpt-3.5-turbo

references to injuries

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

zee

-0.82

tz

-0.80

ullivan

-0.79

zees

-0.77

zsche

-0.76

soDeliveryDate

-0.75

estone

-0.74

ogle

-0.73

arten

-0.71

hist

-0.67

POSITIVE LOGITS

 inflicted

1.29

 incurred

1.10

 sustained

1.01

 suffered

0.95

 injuries

0.88

 inflic

0.87

letal

0.86

 Survivors

0.79

 victims

0.78

 inflicting

0.77

Activations Density 0.031%

descriptions of injuries and medical conditions

references to injuries

No Comments

No Known Activations