INDEX

Explanations

the word "take" in various contexts

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

 Smile

-0.66

 agre

-0.66

Cong

-0.65

holm

-0.64

 accompanies

-0.63

ingen

-0.60

ese

-0.60

lich

-0.60

idding

-0.60

 dissatisf

-0.59

POSITIVE LOGITS

 advantage

1.31

aways

1.24

 aback

1.01

 care

1.00

 precedence

0.96

 refuge

0.96

 heed

0.94

 precautions

0.90

 pains

0.87

 liberties

0.84

Activations Density 0.444%

the word "take" in various contexts

No Comments

No Known Activations