INDEX

Explanations

distinguishing features or various categories within a group

oai_token-act-pair · gpt-3.5-turbo

instances of the word "different" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 faire

-0.72

NP

-0.69

Alert

-0.68

soDeliveryDate

-0.67

Dialogue

-0.66

Main

-0.65

timer

-0.65

ebook

-0.65

NR

-0.65

OIL

-0.63

POSITIVE LOGITS

 kinds

1.18

iating

1.16

 types

1.05

iates

1.03

 iterations

1.01

 combinations

0.99

 ways

0.99

iations

0.98

 varieties

0.97

 variations

0.94

Activations Density 0.031%

distinguishing features or various categories within a group

instances of the word "different" in various contexts

No Comments

No Known Activations