INDEX

Explanations

phrases related to stating opinions or positions

oai_token-act-pair · gpt-3.5-turbo

variations of the letter 's' in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 fret

-0.67

 horses

-0.65

 caps

-0.63

 horse

-0.63

 Spart

-0.60

 Shiva

-0.60

 Alexandria

-0.60

 Strip

-0.60

 Pharaoh

-0.59

 souls

-0.59

POSITIVE LOGITS

pecially

1.54

atisf

1.52

aturated

1.46

lightly

1.39

olved

1.37

olutions

1.34

udden

1.33

ixty

1.32

uddenly

1.32

ensitivity

1.32

Activations Density 0.053%

phrases related to stating opinions or positions

variations of the letter 's' in words

No Comments

No Known Activations