INDEX

Explanations

names of institutions and government-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of governmental or legal institutions and their activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

maxwell

-0.89

 Madison

-0.84

 Indiana

-0.81

 Sioux

-0.80

 Amtrak

-0.80

 Spokane

-0.80

 Jefferson

-0.79

DOD

-0.76

 felony

-0.76

FAA

-0.76

POSITIVE LOGITS

 organise

1.14

 organisers

1.05

 organising

1.02

 organisation

0.97

 recognise

0.97

isation

0.96

ÄŁ

0.95

 organised

0.95

 Programme

0.94

 learnt

0.94

Activations Density 0.833%

names of institutions and government-related terms

mentions of governmental or legal institutions and their activities

No Comments

No Known Activations