INDEX

Explanations

mentions of the political figure "Trump"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "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

NAD

-0.76

iencies

-0.73

ĨĴ

-0.72

 Flavoring

-0.71

 actionGroup

-0.71

++++

-0.69

SAM

-0.67

itial

-0.65

 CentOS

-0.64

ä¸ī

-0.64

POSITIVE LOGITS

 supporters

0.95

care

0.95

TRUMP

0.91

Trump

0.90

Care

0.82

 Donald

0.81

 Supporters

0.80

 impeachment

0.79

 Trump

0.79

eting

0.78

Activations Density 0.053%

mentions of the political figure "Trump"

mentions of the name "Trump."

No Comments

No Known Activations