INDEX

Explanations

mentions of gratitude or recognition

oai_token-act-pair · gpt-3.5-turbo

references to appreciation and acknowledgment of contributions

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

-0.89

-0.80

-0.71

 ceremonial

-0.67

 luxury

-0.67

window

-0.65

 Governors

-0.65

 negoti

-0.64

genic

-0.63

 Schedule

-0.63

POSITIVE LOGITS

 commenters

1.19

 commenter

1.11

 debunk

1.04

 blogs

1.03

 archive

0.96

archive

0.96

blogs

0.95

 archived

0.95

 blogging

0.93

 blog

0.93

Activations Density 1.023%

mentions of gratitude or recognition

references to appreciation and acknowledgment of contributions

No Comments

No Known Activations