INDEX

Explanations

words related to unity and collective action

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 himself

-0.93

 herself

-0.78

ãĥĹ

-0.60

 lucrative

-0.57

 reportedly

-0.57

 disliked

-0.55

 frowned

-0.55

 revoked

-0.54

his

-0.53

 infuri

-0.52

POSITIVE LOGITS

 ourselves

1.83

our

1.71

Our

1.70

Our

1.64

we

1.58

We

1.55

We

1.54

OUR

1.53

we

1.44

 ours

1.32

Activations Density 0.937%

words related to unity and collective action

No Comments

No Known Activations