INDEX

Explanations

discussions and solutions regarding various societal, economic, and political issues

oai_token-act-pair · gpt-3.5-turbo

pronouns and their connections to verbs indicating action or consequence

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

unci

-0.65

Python

-0.65

 Berm

-0.65

ominated

-0.63

inia

-0.63

 Seym

-0.63

Tus

-0.62

types

-0.62

wagen

-0.61

opers

-0.61

POSITIVE LOGITS

 helps

1.31

 prevents

1.27

 enhances

1.23

 enables

1.16

 facilitates

1.16

 strengthens

1.15

 hinder

1.11

 boosts

1.10

 reduces

1.10

 empower

1.10

Activations Density 0.263%

discussions and solutions regarding various societal, economic, and political issues

pronouns and their connections to verbs indicating action or consequence

No Comments

No Known Activations