INDEX

Explanations

references to specific percentages or statistics

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" used 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

USB

-0.78

borgh

-0.69

ALSE

-0.68

 SERV

-0.67

rolet

-0.67

CLASSIFIED

-0.66

bol

-0.66

Completed

-0.65

uin

-0.64

BUS

-0.64

POSITIVE LOGITS

 lieu

1.34

clus

1.22

effic

1.18

 accordance

1.16

efficiency

1.14

 spite

1.12

version

1.07

 conjunction

1.06

clusions

1.02

 disguise

1.02

Activations Density 0.341%

references to specific percentages or statistics

the preposition "in" used in various contexts

No Comments

No Known Activations