INDEX

Explanations

names or proper nouns

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.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

 Pradesh

-0.76

 decomp

-0.76

 Haram

-0.70

urses

-0.70

ctions

-0.64

bably

-0.63

ities

-0.60

 FANT

-0.60

 neglig

-0.60

chio

-0.60

POSITIVE LOGITS

er

1.37

erness

1.28

ers

1.14

ership

1.07

 Twain

0.98

ipl

0.92

ing

0.90

ings

0.90

eer

0.90

ed

0.90

Activations Density 2.898%

names or proper nouns

No Comments

No Known Activations