INDEX

Explanations

phrases related to political news and controversies

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

Negative Logits

quo

-0.66

cum

-0.66

 totality

-0.65

 resting

-0.60

 srfAttach

-0.59

LSD

-0.58

vig

-0.58

 fluids

-0.57

 gratification

-0.57

 bloc

-0.57

POSITIVE LOGITS

akening

1.29

ldon

1.25

eks

1.20

alth

1.19

ird

1.19

ighed

1.17

athered

1.15

bley

1.15

bsite

1.15

instein

1.14

Activations Density 0.112%

phrases related to political news and controversies

No Known Activations