INDEX

Explanations

the expression "more or less"

oai_token-act-pair · gpt-3.5-turbo

phrases that suggest a degree of approximation or uncertainty

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

osa

-0.70

ller

-0.70

 Burgess

-0.68

 Sands

-0.68

hower

-0.67

 Seat

-0.63

amsung

-0.62

 Mitchell

-0.62

icro

-0.61

ividual

-0.60

POSITIVE LOGITS

etheless

0.87

aneously

0.73

ingu

0.67

 desirable

0.67

 likely

0.67

 superficial

0.66

 than

0.66

 mileage

0.64

 aggro

0.63

imate

0.63

Activations Density 0.019%

the expression "more or less"

phrases that suggest a degree of approximation or uncertainty

No Comments

No Known Activations