INDEX

Explanations

names or terms related to "Na" or "Naomi"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "Na" in different contexts

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

 Izan

-0.72

nuts

-0.66

rers

-0.66

 Colossus

-0.64

ttes

-0.64

 espresso

-0.63

 encyclopedia

-0.61

 intersections

-0.61

AGES

-0.60

 directions

-0.59

POSITIVE LOGITS

Ã¯ve

1.26

omi

1.10

ples

1.10

issance

1.08

resh

1.02

uthor

1.00

umann

1.00

elson

0.98

vel

0.96

usal

0.96

Activations Density 0.018%

names or terms related to "Na" or "Naomi"

variations of the word "Na" in different contexts

No Comments

No Known Activations