INDEX

Explanations

phrases related to quality and consistency

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

kens

-0.82

canon

-0.78

ften

-0.77

cart

-0.77

oras

-0.76

apo

-0.74

ptions

-0.73

pole

-0.70

stanbul

-0.70

usra

-0.70

POSITIVE LOGITS

 assurance

1.25

 quality

0.92

Quality

0.92

iller

0.81

 Quality

0.80

 materials

0.75

smanship

0.74

isan

0.71

 goods

0.70

 specimen

0.70

Activations Density 0.812%

phrases related to quality and consistency

No Comments

No Known Activations