INDEX

Explanations

words related to medical treatments and interventions

oai_token-act-pair · gpt-3.5-turbo

terms related to health interventions and their effects

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

DragonMagazine

-0.87

ĳå£«

-0.74

chart

-0.74

Fred

-0.71

License

-0.70

Shadow

-0.69

 Huss

-0.69

worn

-0.68

Tumblr

-0.68

Lenin

-0.68

POSITIVE LOGITS

 therapeutic

1.03

 digestion

1.02

 inflammation

0.99

 therape

0.98

 microbial

0.93

 susceptibility

0.93

 physiological

0.93

 nutrients

0.93

 dietary

0.92

 immunity

0.91

Activations Density 0.224%

words related to medical treatments and interventions

terms related to health interventions and their effects

No Comments

No Known Activations