INDEX

Explanations

medical and clinical study-related terms like "trials", "studies", and "link"

oai_token-act-pair · gpt-3.5-turbo

terms related to clinical trials and studies in health research

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

 possessions

-0.74

 belongings

-0.70

Sev

-0.69

 charm

-0.68

gur

-0.68

 Poles

-0.66

yles

-0.65

scribe

-0.64

wind

-0.64

lo

-0.64

POSITIVE LOGITS

 studies

0.87

Study

0.86

Reviewed

0.83

 conducted

0.82

study

0.82

 published

0.80

 Veter

0.79

 ..............

0.78

 withd

0.78

 Lung

0.78

Activations Density 0.096%

medical and clinical study-related terms like "trials", "studies", and "link"

terms related to clinical trials and studies in health research

No Comments

No Known Activations