INDEX

Explanations

prepositions used in a context of assigning or attributing something to someone

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "on."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ividual

-0.76

elta

-0.68

bidden

-0.68

ancial

-0.66

afety

-0.64

ãĤ¦ãĤ¹

-0.63

é¾įå

-0.63

othal

-0.62

itably

-0.61

aceae

-0.60

POSITIVE LOGITS

on

1.72

ON

1.11

 upon

1.08

 onto

1.07

 atop

1.03

On

1.03

On

1.02

 aboard

0.92

 onstage

0.81

in

0.81

Activations Density 0.315%

prepositions used in a context of assigning or attributing something to someone

occurrences of the word "on."

No Comments

No Known Activations