INDEX

Explanations

the word "to" followed by a verb

oai_token-act-pair · gpt-3.5-turbo

phrases indicating ongoing actions or continuations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.79

 Gujar

-0.72

_.

-0.70

quickShipAvailable

-0.68

 Explan

-0.65

pants

-0.63

 Compass

-0.62

anooga

-0.62

afety

-0.62

 Canary

-0.62

POSITIVE LOGITS

 explore

1.00

 fulfill

0.96

 satisfy

0.96

 pursue

0.94

 accelerate

0.94

 comply

0.94

 strengthen

0.93

 cooperate

0.93

 earn

0.93

 invest

0.92

Activations Density 0.142%

the word "to" followed by a verb

phrases indicating ongoing actions or continuations

No Comments

No Known Activations