INDEX

Explanations

phrases related to providing feedback or commentary on a task

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Kissinger

-0.79

 Rhodes

-0.75

outhern

-0.74

abama

-0.74

 Negro

-0.72

Eastern

-0.71

 Ventura

-0.70

 southern

-0.69

 Okin

-0.69

 Bundy

-0.68

POSITIVE LOGITS

Apps

1.26

ðŁĳ

1.18

iOS

1.16

 iCloud

1.13

iOS

1.12

 usability

1.11

 apps

1.11

 Dropbox

1.10

UX

1.10

ðŁĺ

1.10

Activations Density 0.843%

phrases related to providing feedback or commentary on a task

No Comments

No Known Activations