INDEX

Explanations

references to treaties and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

alach

-0.75

edition

-0.70

gur

-0.68

dose

-0.68

©¶æ

-0.67

shown

-0.67

aptop

-0.66

baugh

-0.65

owler

-0.65

erd

-0.65

POSITIVE LOGITS

 treaty

1.12

 Treaty

1.09

 treaties

0.97

 ratified

0.87

breaker

0.87

 Agreement

0.85

 ratification

0.82

 agreements

0.81

breakers

0.80

reements

0.80

Activations Density 0.007%

references to treaties and their implications

No Comments

No Known Activations