INDEX

Explanations

specific Turkish words

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or entities, particularly in Istanbul

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Diamond

-0.74

 Explorer

-0.70

 Cruise

-0.66

 explorer

-0.65

 Bounty

-0.64

Off

-0.64

 Misc

-0.64

 Liberty

-0.62

 Powers

-0.62

 Juno

-0.61

POSITIVE LOGITS

ÅŁ

4.51

ÄŁ

4.09

Äĩ

2.36

ÅĤ

2.34

Å¡

2.33

ÃŁ

2.18

È

2.15

Ã§

2.05

oÄŁ

1.96

Äį

1.93

Activations Density 0.028%

specific Turkish words

references to specific locations or entities, particularly in Istanbul

No Comments

No Known Activations