INDEX

Explanations

words related to current events and political controversies

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

ties

-0.68

 makeshift

-0.63

 retri

-0.63

Ļ½

-0.61

 perspect

-0.61

mate

-0.59

 isolation

-0.59

graded

-0.58

 contingent

-0.57

 hindsight

-0.57

POSITIVE LOGITS

 Continue

0.99

 Advertisement

0.98

advertisement

0.83

Skip

0.77

Advertisement

0.73

advertising

0.73

ieu

0.72

usercontent

0.70

ADVERTISEMENT

0.70

sburg

0.69

Activations Density 0.281%

words related to current events and political controversies

No Comments

No Known Activations