INDEX

Explanations

rants or critical comments directed towards specific individuals or entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

heit

-0.79

rad

-0.69

senal

-0.68

 extrad

-0.65

aeda

-0.65

 Reincarnated

-0.65

atis

-0.63

ction

-0.62

cius

-0.61

wolves

-0.61

POSITIVE LOGITS

ÂłÂłÂł

0.83

ÂłÂłÂłÂł

0.79

PHOTOS

0.72

Seriously

0.71

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.71

Scroll

0.71

Especially

0.70

ONSORED

0.70

Fans

0.68

????????

0.67

Activations Density 1.463%

rants or critical comments directed towards specific individuals or entities

No Comments

No Known Activations