INDEX

Explanations

mentions of serious medical conditions or injuries

oai_token-act-pair · gpt-3.5-turbo

references to serious injuries or medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Tycoon

-0.98

 Twain

-0.92

soDeliveryDate

-0.82

 Speedway

-0.81

 Telesc

-0.76

dated

-0.73

 Trader

-0.71

Recipe

-0.70

 Journals

-0.69

 philos

-0.68

POSITIVE LOGITS

 injury

0.97

 illness

0.94

 deterioration

0.89

 injuries

0.89

 impairment

0.87

 wounding

0.85

 illnesses

0.83

 offenders

0.83

ities

0.83

 incidents

0.83

Activations Density 0.059%

mentions of serious medical conditions or injuries

references to serious injuries or medical conditions

No Comments

No Known Activations