INDEX

Explanations

proper names

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names and individuals

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

undown

-0.70

eller

-0.69

ĪĴ

-0.69

oxide

-0.66

fml

-0.66

yip

-0.64

 carriers

-0.63

erving

-0.63

 reversible

-0.62

imilar

-0.61

POSITIVE LOGITS

sson

0.69

SAY

0.65

 Cout

0.65

wine

0.64

 Picks

0.64

 Misty

0.64

 Gets

0.64

null

0.63

 Mata

0.62

Rid

0.62

Activations Density 0.095%

proper names

mentions of specific names and individuals

No Comments

No Known Activations