INDEX

Explanations

proper nouns related to a person named Kumar

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Kumar" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

htaking

-0.90

insula

-0.87

*/(

-0.83

¥µ

-0.83

BOOK

-0.80

xp

-0.80

ĻĤ

-0.77

isters

-0.76

ISTER

-0.74

eatures

-0.72

POSITIVE LOGITS

 Sharma

0.92

 Gupta

0.89

 Kumar

0.86

Äį

0.84

pour

0.83

 Sunder

0.82

 Vish

0.82

 Singh

0.80

oglu

0.79

Yad

0.79

Activations Density 0.005%

proper nouns related to a person named Kumar

occurrences of the name "Kumar" and its variations

No Comments

No Known Activations