INDEX

Explanations

phrases related to the potential uses or applications of technology or discoveries

oai_token-act-pair · gpt-3.5-turbo

terms related to potential applications and uses of technologies or discoveries

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

ignt

-0.73

 negro

-0.65

 Cabrera

-0.64

 Pill

-0.62

buck

-0.61

Hai

-0.61

%"

-0.61

 Bers

-0.61

 Tale

-0.60

 Rush

-0.60

POSITIVE LOGITS

ationally

0.87

benefit

0.81

uits

0.80

 applications

0.79

Applications

0.78

hetically

0.76

place

0.75

 usefulness

0.74

conom

0.74

lied

0.73

Activations Density 0.064%

phrases related to the potential uses or applications of technology or discoveries

terms related to potential applications and uses of technologies or discoveries

No Comments

No Known Activations