INDEX

Explanations

statements related to tragic events or 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_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

 PsyNet

-0.68

 Drivers

-0.67

ilon

-0.67

orem

-0.67

 Areas

-0.65

olin

-0.64

catentry

-0.63

Newsletter

-0.62

taboola

-0.61

enh

-0.61

POSITIVE LOGITS

 suddenly

0.93

 blatantly

0.92

 frivol

0.84

 honestly

0.83

 disrespect

0.82

 openly

0.82

 somebody

0.80

someone

0.77

 revered

0.76

 oneself

0.75

Activations Density 2.902%

statements related to tragic events or controversies

No Comments

No Known Activations