INDEX

Explanations

words related to violent and horrifying events or acts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pai

-0.88

pring

-0.74

inoa

-0.73

inion

-0.71

trl

-0.71

arten

-0.71

ailable

-0.71

starter

-0.70

utenant

-0.69

haw

-0.68

POSITIVE LOGITS

 horrors

1.11

 ordeal

1.10

 atrocities

1.09

 tragedies

0.95

 murders

0.94

 scenes

0.94

 torture

0.93

 atroc

0.92

 tale

0.91

 carnage

0.91

Activations Density 0.108%

words related to violent and horrifying events or acts

No Comments

No Known Activations