INDEX

Explanations

phrases indicating a measure or degree of something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating distance or extent

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ycle

-0.69

İĭ

-0.68

spin

-0.67

ortium

-0.67

amine

-0.64

kefeller

-0.62

 Bean

-0.62

 Universe

-0.62

 Syndicate

-0.61

olor

-0.61

POSITIVE LOGITS

fetched

0.73

thing

0.73

bent

0.68

 distances

0.67

points

0.67

Range

0.64

ESA

0.64

rest

0.64

icho

0.63

 distance

0.63

Activations Density 0.012%

phrases indicating a measure or degree of something

phrases indicating distance or extent

No Comments

No Known Activations