INDEX

Explanations

countries and names starting with the letter "S."

oai_token-act-pair · gpt-3.5-turbo

references to geographic locations and place names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ufact

-0.71

addle

-0.67

xual

-0.63

razen

-0.60

culosis

-0.58

ikuman

-0.55

eport

-0.55

 è£ıè

-0.54

oola

-0.54

 pockets

-0.52

POSITIVE LOGITS

 Malf

0.63

 Maced

0.63

 Trails

0.53

 Monteneg

0.53

 Monaco

0.52

 Monstrous

0.52

Ħ¢

0.51

taboola

0.51

tti

0.49

 decaying

0.49

Activations Density 1.029%

countries and names starting with the letter "S."

references to geographic locations and place names

No Comments

No Known Activations