INDEX

Explanations

keywords related to mortality

oai_token-act-pair · gpt-3.5-turbo

references to mortality rates and associated factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

kef

-0.83

Cola

-0.78

xxxxxxxx

-0.77

orney

-0.72

GB

-0.71

ker

-0.70

rab

-0.69

ðĿ

-0.68

NEY

-0.68

bring

-0.67

POSITIVE LOGITS

 mortality

1.01

 contag

0.94

 propensity

0.83

 prevention

0.82

 regress

0.82

 bomber

0.77

 sickness

0.76

 expectancy

0.76

 ridden

0.75

 risk

0.74

Activations Density 0.008%

keywords related to mortality

references to mortality rates and associated factors

No Comments

No Known Activations