INDEX

Explanations

instances where the text mentions looking at or examining something closely

oai_token-act-pair · gpt-3.5-turbo

phrases that instruct the reader to examine or consider something

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

HCR

-0.69

Â¯Â¯Â¯Â¯

-0.66

Balt

-0.65

burgh

-0.64

 await

-0.64

bery

-0.62

blown

-0.61

Jr

-0.61

ARP

-0.60

EMS

-0.60

POSITIVE LOGITS

 yourself

0.75

 google

0.68

 correctly

0.66

 lucky

0.65

iegel

0.64

 perpend

0.63

 minded

0.61

 math

0.61

 maths

0.61

 unlucky

0.58

Activations Density 0.179%

instances where the text mentions looking at or examining something closely

phrases that instruct the reader to examine or consider something

No Comments

No Known Activations