INDEX

Explanations

statements made by individuals

oai_token-act-pair · gpt-3.5-turbo

symbols or characters that may indicate special emphasis or emotional expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

chnology

-0.75

enium

-0.68

atown

-0.66

atre

-0.64

ction

-0.62

chieve

-0.62

odium

-0.60

icy

-0.60

ãĥ¯ãĥ³

-0.60

zbollah

-0.58

POSITIVE LOGITS

said

1.23

 according

0.87

according

0.87

 said

0.83

 says

0.78

ï¸ı

0.70

 exclaimed

0.68

 explained

0.68

 spokesman

0.67

Pg

0.66

Activations Density 0.183%

statements made by individuals

symbols or characters that may indicate special emphasis or emotional expression

No Comments

No Known Activations