INDEX

Explanations

words related to technology, software, and hardware

oai_token-act-pair · gpt-3.5-turbo

specific technical terms and significant nouns that indicate varied contexts such as technology, healthcare, and demographics

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

vez

-0.76

quez

-0.70

wagen

-0.70

 Cheong

-0.68

anon

-0.67

lves

-0.66

ioned

-0.65

glas

-0.64

 Doomsday

-0.64

jad

-0.63

POSITIVE LOGITS

 purposes

1.67

 sake

1.64

ummies

1.14

 reasons

1.10

 purpose

0.85

 eternity

0.81

 foreseeable

0.72

 emergencies

0.72

 liking

0.69

 duration

0.69

Activations Density 0.506%

words related to technology, software, and hardware

specific technical terms and significant nouns that indicate varied contexts such as technology, healthcare, and demographics

No Comments

No Known Activations