INDEX

Explanations

pronouns followed by statements or descriptions

oai_token-act-pair · gpt-3.5-turbo

the word "We" indicating collective or group statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ãĥ¼ãĥ³

-0.66

epad

-0.65

 bothered

-0.61

_>

-0.56

SPONSORED

-0.55

NetMessage

-0.54

-$

-0.54

ouver

-0.53

ãĥ©ãĥ³

-0.52

olor

-0.52

POSITIVE LOGITS

We

2.91

Our

2.17

We

2.09

Our

1.67

we

1.62

WE

1.52

we

1.50

You

1.38

 ourselves

1.37

Let

1.29

Activations Density 0.053%

pronouns followed by statements or descriptions

the word "We" indicating collective or group statements

No Comments

No Known Activations