INDEX

Explanations

semicolons followed by an elaboration or extension of the previous sentence

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

 resil

-0.78

 helicop

-0.75

 unnecess

-0.68

 psychiat

-0.68

 millenn

-0.67

ologically

-0.65

 trou

-0.63

abee

-0.63

 Marine

-0.60

 therap

-0.60

POSITIVE LOGITS

-)

1.32

âĢ¢âĢ¢âĢ¢âĢ¢

0.91

 alternatively

0.86

alias

0.83

âĢ¢âĢ¢

0.75

 thence

0.72

IFF

0.72

;;;;;;;;;;;;

0.71

+)

0.71

////////

0.70

Activations Density 0.042%

semicolons followed by an elaboration or extension of the previous sentence

No Comments

No Known Activations