INDEX

Explanations

phrases related to government actions and reactions

oai_token-act-pair · gpt-3.5-turbo

phrases related to governmental actions or policies

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

EStreamFrame

-0.56

 compat

-0.53

 ancest

-0.49

arc

-0.47

caps

-0.47

Ake

-0.47

ooters

-0.47

 Died

-0.46

 brun

-0.46

affected

-0.46

POSITIVE LOGITS

 antitrust

0.66

 unilaterally

0.60

erity

0.56

 sanction

0.56

 defund

0.56

 approving

0.55

 dictate

0.55

 promulg

0.54

 subsid

0.54

 issuing

0.53

Activations Density 1.317%

phrases related to government actions and reactions

phrases related to governmental actions or policies

No Comments

No Known Activations