INDEX

Explanations

uses of the word "to" in various contexts

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

ukemia

-0.79

otti

-0.71

binding

-0.69

listed

-0.67

ihad

-0.64

 Closing

-0.62

alf

-0.59

lav

-0.59

felt

-0.58

pins

-0.58

POSITIVE LOGITS

 revisit

1.19

 introduce

1.14

ask

1.13

 compare

1.11

 automate

1.10

 educate

1.09

 postpone

1.06

 speculate

1.04

 assume

1.04

 conclude

1.04

Activations Density 0.132%

uses of the word "to" in various contexts

No Comments

No Known Activations