INDEX

Explanations

different organizations and affiliates

oai_token-act-pair · gpt-3.5-turbo

phrases indicating relationships or components of entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

fw

-0.80

 warranted

-0.73

ctive

-0.70

tics

-0.65

Reply

-0.64

oult

-0.64

apy

-0.63

fters

-0.62

metry

-0.62

fter

-0.62

POSITIVE LOGITS

 famed

0.83

 Britain

0.81

 sorts

0.80

etime

0.75

the

0.71

 whom

0.70

 British

0.68

 disgr

0.67

 Belgium

0.67

 Confederation

0.67

Activations Density 0.293%

different organizations and affiliates

phrases indicating relationships or components of entities

No Comments

No Known Activations