INDEX

Explanations

numbers

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Activity

-0.79

Preview

-0.67

Helper

-0.66

Bank

-0.66

Pwr

-0.63

HAM

-0.63

gain

-0.61

 Redemption

-0.60

 Hamb

-0.60

ding

-0.60

POSITIVE LOGITS

 thousand

1.47

eenth

1.22

eteen

1.17

ousand

1.17

 Thousand

1.14

ieth

1.04

 hundred

1.03

 eighty

1.03

fold

1.02

ements

1.02

Activations Density 0.548%

numbers

No Comments

No Known Activations