INDEX

Explanations

references to political entities, specifically the United States

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 Noir

-0.77

 bars

-0.69

 juggling

-0.65

 bottleneck

-0.63

 hust

-0.63

 courtesy

-0.60

 Carbuncle

-0.59

 Emin

-0.59

 Scarlet

-0.59

 jams

-0.58

POSITIVE LOGITS

prising

1.28

nexpected

1.27

PDATED

1.15

gly

1.15

seless

1.13

lyss

1.11

mpire

1.07

pperc

1.04

topia

1.03

psc

1.03

Activations Density 0.551%

references to political entities, specifically the United States

No Comments

No Known Activations