INDEX

Explanations

exact matches and similarities in text

oai_token-act-pair · gpt-3.5-turbo

Instances of the word "exact" and phrases indicating repetition or similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 ashore

-0.83

ipolar

-0.74

too

-0.70

Mub

-0.70

 Beware

-0.68

 challeng

-0.67

 prominently

-0.67

udder

-0.66

 Flavoring

-0.65

 decisively

-0.65

POSITIVE LOGITS

 wording

1.25

itude

1.12

 opposite

1.08

 coordinates

1.03

 same

1.01

ing

0.99

 timing

0.91

 number

0.89

 amount

0.89

 replica

0.88

Activations Density 0.038%

exact matches and similarities in text

Instances of the word "exact" and phrases indicating repetition or similarity

No Comments

No Known Activations