INDEX

Explanations

phrases related to changes and impacts in different areas such as healthcare, politics, and media

oai_token-act-pair · gpt-3.5-turbo

references to healthcare and legal issues

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

)"

-0.68

XY

-0.67

[+

-0.65

)</

-0.64

âĹ¼

-0.60

ãĢ

-0.60

(@

-0.59

 âĢ¦"

-0.58

 ****

-0.58

cc

-0.58

POSITIVE LOGITS

 populist

0.79

 resurg

0.76

 politically

0.72

 populism

0.71

 embattled

0.70

 lawmakers

0.69

 policymakers

0.69

 grassroots

0.67

 politicians

0.66

 homegrown

0.65

Activations Density 2.170%

phrases related to changes and impacts in different areas such as healthcare, politics, and media

references to healthcare and legal issues

No Comments

No Known Activations