INDEX

Explanations

phrases related to official positions, organizations, and government activities

oai_token-act-pair · gpt-3.5-turbo

references to governmental or official entities and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 sucker

-0.77

 gladly

-0.70

sburg

-0.69

blank

-0.68

podcast

-0.65

lees

-0.64

sylv

-0.62

annah

-0.62

åŃĲ

-0.61

apy

-0.61

POSITIVE LOGITS

 Ministry

1.33

 Directorate

1.30

 UNESCO

1.18

 ministries

1.08

 Transport

1.01

 Minister

1.01

 Tourism

1.00

DG

0.97

 ministry

0.96

 Planning

0.95

Activations Density 0.414%

phrases related to official positions, organizations, and government activities

references to governmental or official entities and their actions

No Comments

No Known Activations