INDEX

Explanations

different types of objects, concepts, or categories

oai_token-act-pair · gpt-3.5-turbo

phrases that categorize types of something, particularly in a list format

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

ĸļ

-0.78

ajor

-0.76

esses

-0.70

Ô

-0.69

lists

-0.68

ÅĤ

-0.68

hra

-0.68

arcity

-0.67

pots

-0.67

heid

-0.66

POSITIVE LOGITS

 activity

0.72

 weaponry

0.71

 goods

0.71

 specialty

0.71

 accommodation

0.70

 guiActiveUnfocused

0.69

 medicine

0.69

 fare

0.68

 equipment

0.68

 organism

0.67

Activations Density 0.080%

different types of objects, concepts, or categories

phrases that categorize types of something, particularly in a list format

No Comments

No Known Activations