INDEX

Explanations

geographical locations, specifically cities and universities

oai_token-act-pair · gpt-3.5-turbo

names of specific locations and terms related to immigration and refugee issues

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

Cu

-0.73

buster

-0.68

hij

-0.64

iling

-0.63

 telev

-0.62

 Detective

-0.62

 conglomer

-0.61

 filler

-0.61

ijn

-0.60

Lau

-0.60

POSITIVE LOGITS

throp

2.45

 Arbor

2.25

 Refugees

1.94

kept

1.23

 Kabul

1.07

ickr

1.06

uties

1.04

wcsstore

1.02

atche

1.00

 humane

0.96

Activations Density 0.049%

geographical locations, specifically cities and universities

names of specific locations and terms related to immigration and refugee issues

No Comments

No Known Activations