INDEX

Explanations

words related to various professions, such as philanthropist, film, defensive coordinator, etc

oai_token-act-pair · gpt-3.5-turbo

terms related to various professional roles and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Peb

-0.57

ensional

-0.54

 TAMADRA

-0.54

 Vaugh

-0.53

Kik

-0.50

asonable

-0.48

Bey

-0.48

 Palest

-0.46

tein

-0.46

phasis

-0.46

POSITIVE LOGITS

 trooper

0.53

abilia

0.53

Ĥİ

0.49

 ambassador

0.48

pin

0.48

 worker

0.47

 cyan

0.47

 caucuses

0.45

 troopers

0.44

 Copyright

0.44

Activations Density 0.844%

words related to various professions, such as philanthropist, film, defensive coordinator, etc

terms related to various professional roles and organizations

No Comments

No Known Activations