INDEX

Explanations

proper nouns or names, specifically those related to "Jose"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Jose."

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

ãĤ¤ãĥĪ

-0.79

ICLE

-0.75

 Unicorn

-0.73

Els

-0.72

wealth

-0.68

å¥³

-0.67

åĤ

-0.67

ymph

-0.66

ãĥ¤

-0.64

ickle

-0.64

POSITIVE LOGITS

lins

0.87

upe

0.84

 Jose

0.83

bers

0.83

ber

0.81

keley

0.76

 Francisco

0.76

ppa

0.76

 Earthqu

0.75

ppers

0.74

Activations Density 0.007%

proper nouns or names, specifically those related to "Jose"

references to the name "Jose."

No Comments

No Known Activations