INDEX

Explanations

phrases related to political and legal discussions

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.74

orate

-0.70

istically

-0.69

istical

-0.68

ibilities

-0.67

aciously

-0.67

 proble

-0.66

bably

-0.66

othal

-0.64

thal

-0.63

POSITIVE LOGITS

 ours

0.84

 those

0.78

those

0.74

unts

0.74

Ray

0.68

çĶ°

0.67

ounter

0.65

par

0.63

 myself

0.63

 Graves

0.62

Activations Density 0.056%

phrases related to political and legal discussions

No Comments

No Known Activations