INDEX

Explanations

names of educational institutions

oai_token-act-pair · gpt-3.5-turbo

occurrences mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

RAW

-0.70

 Gork

-0.68

 bunk

-0.67

tery

-0.65

 Zucker

-0.64

 cooker

-0.63

BuyableInstoreAndOnline

-0.60

 Uriel

-0.60

 liking

-0.60

LESS

-0.59

POSITIVE LOGITS

idental

1.40

urring

1.36

urrence

1.36

asionally

1.28

asions

1.24

urred

1.18

asion

1.15

urs

1.12

assion

1.09

ertain

1.05

Activations Density 0.017%

names of educational institutions

occurrences mentioned in the text

No Comments

No Known Activations