INDEX

Explanations

phrases related to the concept of openness, specifically in terms of software and ideas

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

iage

-0.76

CTV

-0.72

rior

-0.65

 endors

-0.63

ãĥīãĥ©ãĤ´ãĥ³

-0.62

grade

-0.61

 Commando

-0.59

doms

-0.59

Avg

-0.57

 constitu

-0.56

POSITIVE LOGITS

 doors

1.04

 Doors

1.03

office

0.87

ource

0.85

 wounds

0.84

 eyed

0.83

 loopholes

0.82

 pores

0.82

 door

0.80

 portals

0.79

Activations Density 3.728%

phrases related to the concept of openness, specifically in terms of software and ideas

No Known Activations