INDEX

Explanations

specific criteria mentioned in text

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to evaluation standards or guidelines

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

joy

-0.72

vironment

-0.71

resent

-0.70

orld

-0.69

ership

-0.69

hand

-0.66

lique

-0.66

owners

-0.65

rodu

-0.65

ston

-0.63

POSITIVE LOGITS

 criteria

1.28

erion

1.01

 criterion

0.98

witz

0.81

 cutoff

0.80

 thresholds

0.78

DragonMagazine

0.72

pillar

0.71

ifiers

0.70

idelines

0.70

Activations Density 0.019%

specific criteria mentioned in text

terms and phrases related to evaluation standards or guidelines

No Comments

No Known Activations