INDEX

Explanations

phrases related to describing details or specific measures outlined in documents

oai_token-act-pair · gpt-3.5-turbo

references to specific sections or details in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 lasted

-0.83

 reinstated

-0.68

 enjoyed

-0.67

 assured

-0.66

 tested

-0.65

 succeeded

-0.65

.–

-0.64

ealous

-0.64

%%

-0.64

casters

-0.64

POSITIVE LOGITS

effic

1.09

humane

1.07

 lieu

1.05

 accordance

1.03

ordinate

1.03

efficiency

1.02

 conjunction

1.01

clus

0.94

appropriately

0.94

animate

0.94

Activations Density 0.215%

phrases related to describing details or specific measures outlined in documents

references to specific sections or details in documents

No Comments

No Known Activations