INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

specific letters or character patterns that may denote types or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

•San

#4 activation: 6.52

No Comments

Negative Logits

 respons

-0.73

 compe

-0.71

?,

-0.68

 thereafter

-0.66

 therefore

-0.65

 bottleneck

-0.65

 encomp

-0.64

 beforehand

-0.64

 presumably

-0.63

 however

-0.62

POSITIVE LOGITS

ONDON

1.05

ANS

1.02

ANA

0.99

reetings

0.98

ALT

0.95

ottenham

0.93

AMD

0.90

ANG

0.89

ENG

0.89

umbai

0.88

Activations Density 0.173%

proper nouns

specific letters or character patterns that may denote types or categories

No Comments

No Known Activations