INDEX

Explanations

mentions of variations or alternatives of a main concept

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating relationships or connections among various subjects or topics

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

Negative Logits

obook

-0.80

ãĤº

-0.77

é¾įå¥ĳå£«

-0.74

ãĤ¼ãĤ¦ãĤ¹

-0.73

rup

-0.69

upiter

-0.69

iamond

-0.69

hower

-0.68

orem

-0.67

orus

-0.67

POSITIVE LOGITS

 including

1.78

 namely

1.65

including

1.44

 notably

1.41

 Including

1.35

such

1.27

 includ

1.27

 such

1.25

 ranging

1.17

 particularly

1.09

Activations Density 0.561%

mentions of variations or alternatives of a main concept

conjunctions and phrases indicating relationships or connections among various subjects or topics

No Known Activations