INDEX

Explanations

the word "paradox" and related variations

oai_token-act-pair · gpt-3.5-turbo

references to paradoxes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Interstitial

-0.85

gars

-0.75

gur

-0.67

astered

-0.67

RAW

-0.66

aina

-0.66

OTT

-0.64

VEL

-0.63

rations

-0.63

Ķ

-0.63

POSITIVE LOGITS

 paradox

1.23

 Paradox

1.15

ioned

1.05

ical

1.04

ically

0.98

ively

0.84

es

0.80

ional

0.78

 puzz

0.75

ibly

0.75

Activations Density 0.008%

the word "paradox" and related variations

references to paradoxes

No Comments

No Known Activations