INDEX

Explanations

phrases related to criminal activities or incidents

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

obyl

-0.74

osate

-0.68

eb

-0.62

ogenic

-0.60

âĸĪâĸĪâĸĪâĸĪ

-0.58

emin

-0.55

oths

-0.55

²¾

-0.55

hibition

-0.55

atible

-0.55

POSITIVE LOGITS

 sources

0.78

 spokesman

0.77

 spokeswoman

0.76

aretz

0.66

 Reuters

0.65

AFP

0.64

reports

0.64

 examiner

0.64

source

0.63

 disclose

0.62

Activations Density 1.278%

phrases related to criminal activities or incidents

No Comments

No Known Activations