INDEX

Explanations

phrases related to statistical analysis or medical testing

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases that indicate relationships or connections between ideas

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

meet

-0.87

ollo

-0.78

Ĥİ

-0.77

pees

-0.75

DAY

-0.74

Shut

-0.74

Times

-0.73

å¥³

-0.72

aws

-0.71

wire

-0.70

POSITIVE LOGITS

 consequently

1.18

 hence

1.17

 therefore

1.15

 thereby

1.15

rogen

1.08

 thus

1.06

rogens

1.06

 optionally

1.04

 subsequently

1.03

 consequ

1.02

Activations Density 0.666%

phrases related to statistical analysis or medical testing

conjunctions and phrases that indicate relationships or connections between ideas

No Comments

No Known Activations