INDEX

Explanations

phrases with the word "ir" followed by a number and potentially another word

oai_token-act-pair · gpt-3.5-turbo

variations of the term "irrefutable."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 guiActiveUnfocused

-0.78

ezvous

-0.76

soDeliveryDate

-0.75

erker

-0.71

 CLSID

-0.71

hetti

-0.71

 Vinyl

-0.68

yards

-0.67

ership

-0.67

translation

-0.67

POSITIVE LOGITS

cles

1.05

relevant

0.93

respective

0.92

idium

0.91

rational

0.80

regular

0.79

religious

0.79

respons

0.78

anian

0.78

ilateral

0.77

Activations Density 0.018%

phrases with the word "ir" followed by a number and potentially another word

variations of the term "irrefutable."

No Comments

No Known Activations