INDEX

Explanations

verbs indicating likelihood or probability

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate likelihood or statistical comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

books

-0.78

Cooldown

-0.74

yrights

-0.73

eport

-0.72

limits

-0.72

inelli

-0.68

soDeliveryDate

-0.68

hai

-0.67

anooga

-0.67

RAW

-0.67

POSITIVE LOGITS

 engage

1.06

 participate

1.04

be

1.04

 receive

1.03

 confront

1.02

 earn

1.02

 absorb

0.98

 reject

0.97

 accumulate

0.97

 accept

0.96

Activations Density 0.055%

verbs indicating likelihood or probability

phrases that indicate likelihood or statistical comparisons

No Comments

No Known Activations