INDEX

Explanations

instances of prepositions or phrases indicating a relationship between entities

oai_token-act-pair · gpt-3.5-turbo

prepositions and their usage in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 =================

-0.66

 Revis

-0.65

 Claus

-0.63

 happily

-0.62

 âī

-0.61

 meanwhile

-0.60

 accommod

-0.60

 altern

-0.59

inn

-0.57

 emphatically

-0.56

POSITIVE LOGITS

roads

1.07

breeding

1.07

ings

1.05

conom

1.05

effic

1.04

gs

1.02

icular

1.02

laws

1.02

days

1.01

nesses

1.00

Activations Density 0.517%

instances of prepositions or phrases indicating a relationship between entities

prepositions and their usage in various contexts

No Comments

No Known Activations