INDEX

Explanations

adjectives describing a particular type or category of something

oai_token-act-pair · gpt-3.5-turbo

phrases that describe types or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 VIDEOS

-0.71

å§«

-0.68

milo

-0.65

 Bars

-0.62

omer

-0.62

heid

-0.61

INA

-0.60

 Vulkan

-0.60

ilaterally

-0.60

æķ

-0.58

POSITIVE LOGITS

liest

0.94

lihood

0.73

 thing

0.69

etting

0.66

liness

0.63

etter

0.61

linger

0.60

hearted

0.60

hest

0.59

bright

0.59

Activations Density 0.040%

adjectives describing a particular type or category of something

phrases that describe types or categories

No Comments

No Known Activations