INDEX

Explanations

phrases related to objects or systems that are composed of two or more parts

oai_token-act-pair · gpt-3.5-turbo

references to quantities and structures involving pairs or groups

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

ifice

-0.73

IAS

-0.72

asta

-0.71

jury

-0.70

ugu

-0.70

akings

-0.67

UNE

-0.66

lus

-0.64

lov

-0.63

employment

-0.63

POSITIVE LOGITS

 distinct

1.21

 separate

1.10

fold

1.07

 dozen

1.04

 hundred

1.00

 consecutive

0.99

 different

0.99

 pairs

0.99

 thirds

0.99

 dimensional

0.99

Activations Density 0.194%

phrases related to objects or systems that are composed of two or more parts

references to quantities and structures involving pairs or groups

No Comments

No Known Activations