INDEX

Explanations

times expressed in the format of hours and minutes

oai_token-act-pair · gpt-3.5-turbo

specific times of day and associated time formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lessly

-0.74

rival

-0.68

ĸļ

-0.68

rics

-0.67

apego

-0.67

raltar

-0.65

alogy

-0.64

 STATS

-0.63

 wrongly

-0.62

hetically

-0.62

POSITIVE LOGITS

pm

1.10

pm

1.08

PM

1.03

AM

0.98

GMT

0.92

UTC

0.90

hrs

0.85

 noon

0.84

PST

0.82

AM

0.80

Activations Density 0.048%

times expressed in the format of hours and minutes

specific times of day and associated time formats

No Comments

No Known Activations