INDEX

Explanations

phrases indicating anticipation or prediction

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate foreshadowing or predictions about future events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Cosponsors

-0.66

 biod

-0.65

ongh

-0.63

 bases

-0.63

orted

-0.61

 emphasizes

-0.61

 Citation

-0.60

 prism

-0.60

 retention

-0.59

 anonym

-0.59

POSITIVE LOGITS

 looming

1.15

 awaits

1.15

 await

1.09

 unfold

1.08

fall

1.06

 imminent

1.03

 unfolding

1.01

 impending

0.98

 awaited

0.98

 brewing

0.98

Activations Density 0.336%

phrases indicating anticipation or prediction

phrases that indicate foreshadowing or predictions about future events

No Comments

No Known Activations