INDEX

Explanations

the word "right" used to indicate correctness or direction

oai_token-act-pair · gpt-3.5-turbo

phrases indicating correctness or accuracy

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

igmat

-0.71

ipation

-0.70

leneck

-0.64

mat

-0.62

ulz

-0.61

ĸļ

-0.61

arettes

-0.60

ains

-0.60

arette

-0.59

irl

-0.59

POSITIVE LOGITS

eous

1.14

shore

0.80

 smack

0.78

 wing

0.76

ocrin

0.73

eering

0.71

 winger

0.69

å¾

0.68

 fielder

0.67

hand

0.67

Activations Density 0.047%

the word "right" used to indicate correctness or direction

phrases indicating correctness or accuracy

No Comments

No Known Activations