INDEX

Explanations

mentions of President Trump and his actions or statements

oai_token-act-pair · gpt-3.5-turbo

possessive constructions referencing Donald Trump

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

lehem

-0.87

hari

-0.86

":[

-0.76

 Rowling

-0.75

anges

-0.75

lin

-0.73

lling

-0.68

 Logged

-0.68

liga

-0.68

 Kubrick

-0.67

POSITIVE LOGITS

own

1.30

 newest

1.05

 penchant

1.00

 signature

0.97

 insistence

0.97

 plight

0.96

 inability

0.95

 efforts

0.95

 antics

0.94

 newfound

0.94

Activations Density 0.161%

mentions of President Trump and his actions or statements

possessive constructions referencing Donald Trump

No Comments

No Known Activations