INDEX

Explanations

phrases related to changes in leadership roles

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

Catalog

-0.78

insk

-0.68

icons

-0.66

Els

-0.65

Collection

-0.65

NG

-0.64

sylv

-0.64

inal

-0.62

aida

-0.61

alos

-0.61

POSITIVE LOGITS

 abruptly

1.03

 altogether

0.93

uting

0.89

 midway

0.87

 voluntarily

0.84

 entirely

0.82

 retiring

0.79

 prematurely

0.79

 overseeing

0.77

utive

0.77

Activations Density 0.160%

phrases related to changes in leadership roles

No Comments

No Known Activations