INDEX

Explanations

references to unspecified alternative options or considerations

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

utenant

-0.77

ony

-0.70

opus

-0.70

zai

-0.68

wark

-0.68

 ç¥ŀ

-0.68

enced

-0.63

 flanked

-0.61

 Retrieved

-0.61

iste

-0.60

POSITIVE LOGITS

worldly

2.06

 kinds

1.21

 aspects

1.20

 countries

1.12

 avenues

1.12

 factors

1.11

 types

1.10

 forms

1.06

 ways

1.02

 disciplines

1.01

Activations Density 0.090%

references to unspecified alternative options or considerations

No Comments

No Known Activations