INDEX

Explanations

business or organization names

oai_token-act-pair · gpt-3.5-turbo

specific entities or titles related to events or situations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agy

-0.59

yss

-0.57

ocious

-0.53

ï¸ı

-0.52

itiveness

-0.51

aneous

-0.51

rational

-0.50

Houston

-0.48

vious

-0.47

ongyang

-0.45

POSITIVE LOGITS

isine

0.60

Ô

0.58

azeera

0.56

 Emirates

0.55

 Alam

0.55

llah

0.55

iets

0.54

ukong

0.53

ãĤ¼ãĤ¦ãĤ¹

0.52

 Leone

0.52

Activations Density 1.083%

business or organization names

specific entities or titles related to events or situations

No Comments

No Known Activations