INDEX

Explanations

phrases related to accountability or responsibility

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

Not in Any Lists

No Comments

Negative Logits

tein

-0.79

improve

-0.69

tering

-0.62

gran

-0.62

frey

-0.61

cher

-0.59

division

-0.59

 ascending

-0.58

TON

-0.58

buff

-0.58

POSITIVE LOGITS

Ohio

0.80

oka

0.74

 citiz

0.72

amaz

0.70

 solely

0.68

 responsible

0.67

 Cosponsors

0.67

ģĸ

0.66

atics

0.66

ativity

0.66

Activations Density 0.025%

phrases related to accountability or responsibility

No Comments

No Known Activations