INDEX

Explanations

mentions of controversial or newsworthy events or topics

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

¬¼

-0.74

ãģ®

-0.72

iph

-0.66

ISE

-0.65

eker

-0.64

ãĤĬ

-0.63

vised

-0.63

EO

-0.63

º

-0.62

oir

-0.61

POSITIVE LOGITS

 there

0.88

there

0.80

 namely

0.73

it

0.72

we

0.70

 respectively

0.70

 however

0.69

 albeit

0.67

 they

0.67

 nevertheless

0.66

Activations Density 1.037%

mentions of controversial or newsworthy events or topics

No Comments

No Known Activations