INDEX

Explanations

words related to tools or devices

oai_token-act-pair · gpt-3.5-turbo

references to distinct groups of individuals or communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Bahrain

-0.68

uncture

-0.64

 investigations

-0.64

 issuance

-0.62

 maneuvers

-0.60

 sudden

-0.59

×Ķ

-0.58

 subdu

-0.58

 final

-0.57

 forfeiture

-0.57

POSITIVE LOGITS

weet

1.22

geist

1.18

poon

1.07

pace

1.03

rane

1.01

poons

0.97

hirt

0.97

ters

0.95

peed

0.95

rors

0.95

Activations Density 0.017%

words related to tools or devices

references to distinct groups of individuals or communities

No Comments

No Known Activations