INDEX

Explanations

technical terms related to computer programming and technology

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

hement

-0.72

HOU

-0.68

plet

-0.65

 latter

-0.59

 taps

-0.59

ulus

-0.58

feed

-0.58

lou

-0.58

 commits

-0.56

 rolls

-0.56

POSITIVE LOGITS

ccording

1.25

Throughout

0.91

Initially

0.86

Although

0.84

 Initially

0.82

Whether

0.82

Sometimes

0.81

Aside

0.80

 Throughout

0.80

 Firstly

0.80

Activations Density 0.720%

technical terms related to computer programming and technology

No Comments

No Known Activations