INDEX

Explanations

passive voice constructions indicating an action that has already taken place

oai_token-act-pair · gpt-3.5-turbo

the phrase "had been" in various contexts

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

ively

-0.70

rones

-0.70

ives

-0.67

iveness

-0.62

rates

-0.60

essee

-0.60

anth

-0.60

($

-0.60

arta

-0.60

erity

-0.60

POSITIVE LOGITS

 able

0.97

wolves

0.93

cffffcc

0.93

 subjected

0.92

 beaten

0.89

 mistaken

0.87

 notified

0.85

 replaced

0.84

 blown

0.84

 treated

0.83

Activations Density 0.103%

passive voice constructions indicating an action that has already taken place

the phrase "had been" in various contexts

No Comments

No Known Activations