INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of a specific name or term in the document

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

zzi

-0.76

 Zombie

-0.72

 Apocalypse

-0.70

ggle

-0.70

hiba

-0.64

senal

-0.63

 veget

-0.58

 Goods

-0.57

 Wolves

-0.57

 Inferno

-0.57

POSITIVE LOGITS

osate

1.22

sburg

1.07

anasia

1.06

shire

1.03

ouse

0.96

sburgh

0.95

reys

0.95

edIn

0.93

umbing

0.89

rity

0.89

Activations Density 0.018%

proper nouns

the repeated mention of a specific name or term in the document

No Comments

No Known Activations