INDEX

Explanations

proper names

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people

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

ACTED

-0.74

 guiIcon

-0.74

 thereto

-0.70

Ħ¢

-0.64

 thereof

-0.64

 prevailing

-0.64

 disg

-0.63

opausal

-0.62

 initiating

-0.62

 tender

-0.61

POSITIVE LOGITS

anyahu

0.92

jamin

0.90

ston

0.90

olyn

0.88

Berry

0.87

odore

0.86

resa

0.84

xiety

0.84

cohol

0.83

hesda

0.80

Activations Density 0.275%

proper names

proper nouns, specifically names of people

No Comments

No Known Activations