INDEX

Explanations

phrases related to completeness or totality

oai_token-act-pair · gpt-3.5-turbo

phrases indicating totality or completeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

maid

-0.79

hops

-0.75

spr

-0.73

GES

-0.70

olson

-0.69

rium

-0.68

uds

-0.68

paces

-0.67

uay

-0.67

hots

-0.67

POSITIVE LOGITS

 strangers

1.22

 stranger

1.09

 disregard

1.07

 lack

0.99

 meltdown

0.95

 annihilation

0.94

 beginners

0.93

 absence

0.93

 overhaul

0.91

 domination

0.90

Activations Density 0.061%

phrases related to completeness or totality

phrases indicating totality or completeness

No Comments

No Known Activations