INDEX

Explanations

time-related information in the format "number/number"

oai_token-act-pair · gpt-3.5-turbo

references to time periods, specifically durations given in hours

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

 speeches

-0.70

 plank

-0.70

 bubbles

-0.69

 Tornado

-0.67

erto

-0.66

 tornado

-0.66

nod

-0.63

 Methodist

-0.63

 runs

-0.62

 velvet

-0.62

POSITIVE LOGITS

etc

1.24

oct

1.01

0.98

0.94

ËĪ

0.91

Flickr

0.90

Pg

0.90

Getty

0.88

âĪ

0.87

Activations Density 0.053%

time-related information in the format "number/number"

references to time periods, specifically durations given in hours

No Comments

No Known Activations