INDEX

Explanations

technical terms related to programming, development processes, and evaluations

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

@@

-0.71

%%%%

-0.62

tery

-0.57

@@

-0.55

 Printed

-0.54

 Bite

-0.54

packages

-0.53

 Takes

-0.53

 Skip

-0.53

 CODE

-0.53

POSITIVE LOGITS

 extent

1.61

venge

1.40

 detriment

1.37

 tune

1.12

rouse

1.07

 fullest

1.04

 liking

0.96

 degree

0.91

merce

0.90

 conclusion

0.86

Activations Density 1.283%

technical terms related to programming, development processes, and evaluations

No Comments

No Known Activations