INDEX

Explanations

phrases related to specific entities such as NFL, CIA, macronutrients, Ford pickups, Lib Dem voters, NHL teams, South Carolina law enforcement, U.S. State Department, IRS official Lois Lerner, Disney characters, and more

oai_token-act-pair · gpt-3.5-turbo

mentions of specific organizations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

anwhile

-0.64

 Beir

-0.57

 Canaver

-0.57

 Decay

-0.53

 Maurit

-0.52

 Carbuncle

-0.51

 Curiosity

-0.51

 Spiel

-0.51

 Duffy

-0.50

lain

-0.49

POSITIVE LOGITS

assets

0.57

 workforce

0.54

isations

0.51

 outings

0.47

 hairst

0.47

 conco

0.47

 wardrobe

0.46

 haul

0.46

 asset

0.46

ÂŃ

0.46

Activations Density 2.056%

phrases related to specific entities such as NFL, CIA, macronutrients, Ford pickups, Lib Dem voters, NHL teams, South Carolina law enforcement, U.S. State Department, IRS official Lois Lerner, Disney characters, and more

mentions of specific organizations or institutions

No Comments

No Known Activations