INDEX

Explanations

mentions of decision-making and planning in political or official 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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

@#&

-0.73

iuses

-0.66

 mistakenly

-0.64

quartered

-0.63

 dich

-0.62

 wandered

-0.61

 wrongly

-0.61

pired

-0.59

rote

-0.59

 Wrong

-0.59

POSITIVE LOGITS

 someday

1.56

 tomorrow

1.56

1.40

morrow

1.39

1.30

1.27

 next

1.23

 sooner

1.22

 soon

1.22

soon

1.16

Activations Density 9.040%

mentions of decision-making and planning in political or official contexts

No Comments

No Known Activations