INDEX

Explanations

proper names and surnames

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people or places

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ay

-0.75

 Pradesh

-0.67

 bowl

-0.64

 DRAG

-0.61

 sham

-0.60

sul

-0.60

 Sakura

-0.60

 envy

-0.59

Tube

-0.58

 Naruto

-0.57

POSITIVE LOGITS

enberg

1.37

lein

1.36

meier

1.30

meyer

1.21

linger

1.20

mann

1.18

lund

1.16

inski

1.15

stein

1.14

ner

1.13

Activations Density 0.196%

proper names and surnames

proper nouns, particularly names of people or places

No Comments

No Known Activations