INDEX

Explanations

references to time intervals, specifically when they mention "daytime" or "nighttime"

oai_token-act-pair · gpt-3.5-turbo

references to times of day, particularly "daytime" and "nighttime."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

IAN

-0.82

Dat

-0.75

kson

-0.75

NES

-0.71

AMI

-0.71

 Sett

-0.70

Asset

-0.69

legram

-0.69

 Drill

-0.68

toe

-0.67

POSITIVE LOGITS

urnal

1.37

etheless

0.95

 daytime

0.87

 nighttime

0.81

 glare

0.79

 sighting

0.77

 brightness

0.77

 livest

0.76

iries

0.76

 unsus

0.75

Activations Density 0.018%

references to time intervals, specifically when they mention "daytime" or "nighttime"

references to times of day, particularly "daytime" and "nighttime."

No Comments

No Known Activations