INDEX

Explanations

prepositions followed by nouns

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate addition or inclusion of ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

marine

-0.75

DOWN

-0.74

oris

-0.71

ANS

-0.71

Reviewer

-0.70

Sport

-0.69

dayName

-0.67

notice

-0.66

down

-0.66

oiler

-0.64

POSITIVE LOGITS

 providing

0.82

 being

0.82

 supplying

0.73

 producing

0.72

 benefiting

0.71

 exhibiting

0.70

 confirming

0.70

wards

0.69

 possessing

0.68

 creating

0.68

Activations Density 0.037%

prepositions followed by nouns

phrases that indicate addition or inclusion of ideas

No Comments

No Known Activations