INDEX

Explanations

mentions of a specific term, possibly related to a brand or platform, which is "Ins"

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "ins."

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

erous

-0.65

llan

-0.65

ries

-0.65

 Sigma

-0.64

cha

-0.63

 Baird

-0.63

 distortions

-0.61

âĢ¢âĢ¢

-0.58

 ÙĪ

-0.58

 mates

-0.57

POSITIVE LOGITS

urance

1.46

ufficient

1.45

omnia

1.43

urrection

1.33

ights

1.33

ensitive

1.31

iders

1.29

ulin

1.27

pect

1.27

ider

1.23

Activations Density 0.015%

mentions of a specific term, possibly related to a brand or platform, which is "Ins"

instances of the prefix "ins."

No Comments

No Known Activations