INDEX

Explanations

mentions of physical displays or exhibitions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "display" and its variations

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

trak

-0.79

istani

-0.76

externalActionCode

-0.75

shaw

-0.74

lake

-0.68

leans

-0.64

ILL

-0.64

SOURCE

-0.63

owsky

-0.62

 injection

-0.61

POSITIVE LOGITS

 displays

1.08

 prominently

0.95

 Thumbnails

0.94

 display

0.93

igators

0.91

 exhibits

0.85

 Display

0.78

display

0.75

igator

0.75

 banners

0.74

Activations Density 0.017%

mentions of physical displays or exhibitions

instances of the word "display" and its variations

No Comments

No Known Activations